{ "schemaVersion": "1.0", "name": "BenchLM models", "description": "Stable model metadata, rankings, benchmark scores, and coverage fields for BenchLM model pages.", "canonicalUrl": "https://benchlm.ai/data/models.json", "generatedAt": "2026-06-12T20:35:11.146Z", "sourceLastUpdated": "June 12, 2026", "sourceFiles": [ "src/data/benchmarks.json", "src/data/provenance.js", "src/data/modelReleaseMetadata.js" ], "counts": { "totalModels": 258, "canonicalModels": 175, "rankingEligibleModels": 123 }, "items": [ { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 99, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md", "id": 9, "releaseDate": "2026-06-09", "market": null, "isRegional": false, "family": { "familyKey": "claude-mythos", "familyName": "Claude Mythos", "variantType": "restricted", "snapshotLabel": null, "baseFamilyModelKey": "claude-mythos", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 99, "overallScore": 99, "rawOverallScore": 99, "verifiedDisplayScore": 85, "displayCategoryScores": { "agentic": 100, "coding": 100, "reasoning": null, "multimodalGrounded": 98.9, "knowledge": 99.5, "multilingual": 100, "instructionFollowing": 91.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 87, "coding": 85.9, "reasoning": null, "multimodalGrounded": 92.7, "knowledge": 74.6, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 1, "categoryRanks": { "agentic": 1, "coding": 1, "multimodalGrounded": 2, "multilingual": 1, "instructionFollowing": 17 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 25, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 88, "osWorldVerified": 85, "browseComp": 88, "gdpvalAa": 1932 }, "coding": { "sweVerified": 95.5, "swePro": 80.3, "frontierCode": 29.3, "terminalBench2": 88 }, "reasoning": {}, "multimodalGrounded": { "mmmuPro": 92.7, "sweMultimodal": 54.9, "charxiv": 93.5, "charxivNoTools": 88.9, "blueprintBench2": 38.6 }, "knowledge": { "gpqa": 94.1, "hle": 64.5, "hleNoTools": 59 }, "multilingual": { "sweMultilingual": 92.2 }, "instructionFollowing": {}, "math": { "usamo2026": 97.6 }, "external": { "exploitBench": 78 } } }, { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 97, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md", "id": 257, "releaseDate": "2026-06-09", "market": null, "isRegional": false, "family": { "familyKey": "claude-fable", "familyName": "Claude Fable", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-fable-5", "relatedModelKeys": [ "claude-mythos-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 97, "overallScore": 96, "rawOverallScore": 96, "verifiedDisplayScore": 85, "displayCategoryScores": { "agentic": 100, "coding": 100, "reasoning": null, "multimodalGrounded": 79, "knowledge": 99.8, "multilingual": 100, "instructionFollowing": 92.7, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 85.2, "coding": 85.6, "reasoning": null, "multimodalGrounded": 92.4, "knowledge": 74.8, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 2, "categoryRanks": { "agentic": 2, "coding": 2, "multimodalGrounded": 18, "multilingual": 2, "instructionFollowing": 12 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 28, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 84.3, "osWorldVerified": 85, "browseComp": 86.9, "gdpvalAa": 1932 }, "coding": { "sweVerified": 95, "swePro": 80, "frontierCode": 29.3, "terminalBench2": 84.3 }, "reasoning": {}, "multimodalGrounded": { "mmmuPro": 92.7, "sweMultimodal": 59, "charxiv": 93.2, "charxivNoTools": 86.1, "blueprintBench2": 38.6 }, "knowledge": { "gpqa": 94.5, "hle": 64.5, "hleNoTools": 59 }, "multilingual": { "sweMultilingual": 87.3 }, "instructionFollowing": {}, "math": { "usamo2026": 97.6 }, "external": { "exploitBench": 78 } } }, { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 93, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "id": 238, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-8", "familyName": "Claude Opus 4.8", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-8", "relatedModelKeys": [ "claude-opus-4-7-max", "claude-opus-4-7", "claude-opus-4-6" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-opus-4-7-max" }, "scores": { "displayScore": 93, "overallScore": 92, "rawOverallScore": 92, "verifiedDisplayScore": 76, "displayCategoryScores": { "agentic": 96.4, "coding": 98, "reasoning": null, "multimodalGrounded": 66.4, "knowledge": 98.7, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 80.1, "coding": 76.4, "reasoning": null, "multimodalGrounded": 76.1, "knowledge": 70.1, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 3, "categoryRanks": { "agentic": 3, "coding": 3, "multimodalGrounded": 36, "knowledge": 2 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 74.6, "browseComp": 84.3, "deepSearchQa": 93.1, "osWorldVerified": 83.4, "financeAgentV2": 53.9, "gdpvalAa": 1890, "mcpAtlas": 82.2, "toolathlon": 59.9, "gertLabs": 72.97, "aaAgenticIndex": 77.81, "tau2Bench": 94.4, "gdpvalAaNormalized": 69.5 }, "coding": { "sweVerified": 88.6, "swePro": 69.2, "sweMultilingual": 84.4, "sweMultimodal": 38.4, "terminalBench2": 74.6, "cursorBench31": 58.4, "aaCodingIndex": 56.71, "terminalBenchHard": 58.3, "aaSciCode": 53.5 }, "reasoning": { "lcr": 67.7, "critpt": 20.9 }, "multimodalGrounded": { "officeQaPro": 66.2, "screenSpotPro": 87.9, "charxiv": 89.9, "charxivNoTools": 80.5, "designArenaWebsite": 1284 }, "knowledge": { "gpqa": 93.6, "gpqaDiamond": 93.6, "hle": 57.9, "hleNoTools": 49.8, "artificialAnalysis": 61.44, "aaGpqaDiamond": 92, "aaHle": 45.7, "aaOmniscienceIndex": 27.4, "omniscienceAccuracy": 46.6, "omniscienceHallucinationRate": 35.9 }, "multilingual": { "include": 87.6 }, "instructionFollowing": { "aaIfBench": 62.2 }, "math": { "usamo2026": 96.7 } } }, { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 91, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md", "id": 14, "releaseDate": "2026-02-19", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-1-pro", "familyName": "Gemini 3.1 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-1-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 91, "overallScore": 89, "rawOverallScore": 89, "verifiedDisplayScore": 79, "displayCategoryScores": { "agentic": 81.6, "coding": 93, "reasoning": 96.4, "multimodalGrounded": 84, "knowledge": 93.9, "multilingual": 100, "instructionFollowing": 93.4, "math": 67.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 77.1, "multimodalGrounded": 82.8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 4, "categoryRanks": { "agentic": 13, "coding": 5, "reasoning": 2, "multimodalGrounded": 14, "knowledge": 4, "multilingual": 3, "instructionFollowing": 10, "math": 37 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 49, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "clawEval": 57.8, "deepSearchQa": 69.7, "tau2Bench": 95.6, "aaAgenticIndex": 59.09, "apexAgentsAa": 32, "gdpvalAaNormalized": 40.7, "gdpvalAa": 1314, "gertLabs": 56.87 }, "coding": { "liveCodeBenchPro": 82.9, "reactNativeEvals": 78.9, "vibeCodeBench": 32.034, "aaCodingIndex": 55.5, "terminalBenchHard": 53.8, "aaSciCode": 58.9 }, "reasoning": { "arcAgi2": 77.1, "lcr": 72.7, "critpt": 17.7 }, "multimodalGrounded": { "mmmuPro": 83.9, "charxiv": 80.2, "erqa": 69.4, "simpleVqa": 72.4, "screenSpotPro": 84.4, "zeroBench": 29, "medXpertQaMm": 81.3, "gdpvalAa": 1320, "aaMmmuPro": 82.4, "designArenaWebsite": 1296 }, "knowledge": { "gpqaDiamond": 94.3, "hleNoTools": 45.4, "healthBenchHard": 20.6, "medXpertQaText": 71.5, "artificialAnalysis": 57.18, "aaGpqaDiamond": 94.1, "aaHle": 44.7, "aaOmniscienceIndex": 32.9, "omniscienceAccuracy": 55.3, "omniscienceHallucinationRate": 49.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 77.1 }, "math": {} } }, { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 91, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "id": 15, "releaseDate": "2026-05-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-7-max", "familyName": "Qwen3.7 Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-7-max", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 91, "overallScore": 89, "rawOverallScore": 89, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 86.9, "coding": 91.6, "reasoning": 94.8, "multimodalGrounded": null, "knowledge": 85.9, "multilingual": 84, "instructionFollowing": 93.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 69.7, "coding": 73.6, "reasoning": 90.4, "multimodalGrounded": null, "knowledge": 71.2, "multilingual": 87, "instructionFollowing": 89, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 5, "categoryRanks": { "coding": 6, "knowledge": 10, "multilingual": 13, "instructionFollowing": 11 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 33, "verifiedBenchmarkCount": 33, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 69.7, "qwenClawBench": 64.3, "qwenWebBench": 1568, "clawEval": 65.2, "bfclV4": 75, "mcpAtlas": 76.4, "vitaBench": 47.9, "hleWithTools": 53.5, "aaAgenticIndex": 66.56, "tau2Bench": 94.7, "gdpvalAaNormalized": 52.2, "gdpvalAa": 1543, "gertLabs": 64.27 }, "coding": { "sweVerified": 80.4, "swePro": 60.6, "sweMultilingual": 78.3, "nl2Repo": 47.2, "sciCode": 53.5, "liveCodeBench": 91.6, "terminalBench2": 69.7, "aaCodingIndex": 50.12, "terminalBenchHard": 50.8, "aaSciCode": 48.8 }, "reasoning": { "mrcrv2": 90.4, "critpt": 13.4, "lcr": 69 }, "multimodalGrounded": { "designArenaWebsite": 1307 }, "knowledge": { "gpqa": 92.4, "gpqaDiamond": 92.4, "hle": 41.4, "mmluPro": 89.6, "mmluRedux": 95, "superGpqa": 73.6, "mmmlu": 90.3, "artificialAnalysis": 56.58, "aaGpqaDiamond": 92.3, "aaHle": 38.1, "aaOmniscienceIndex": 14.1, "omniscienceAccuracy": 30.1, "omniscienceHallucinationRate": 22.9 }, "multilingual": { "mmluProX": 87, "nova63": 59, "include": 86.2, "maxife": 89.2, "polyMath": 86.5 }, "instructionFollowing": { "ifeval": 94.3, "ifBench": 79.1, "aaIfBench": 80.5 }, "math": { "hmmtFeb2026": 97.1, "imoAnswerBench": 90, "apex": 44.5 } } }, { "slug": "gpt-5-4-pro", "canonicalModelKey": "gpt-5-4-pro", "model": "GPT-5.4 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 90, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/gpt-5-4-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-pro.md", "id": 40, "releaseDate": "2026-03-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-mini", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 90, "overallScore": 89, "rawOverallScore": 89, "verifiedDisplayScore": 79, "displayCategoryScores": { "agentic": 89.6, "coding": 90.6, "reasoning": 97.5, "multimodalGrounded": 100, "knowledge": 59.9, "multilingual": null, "instructionFollowing": 93.7, "math": 92.8 }, "verifiedDisplayCategoryScores": { "agentic": 89.3, "coding": null, "reasoning": 83.3, "multimodalGrounded": 94, "knowledge": 49, "multilingual": null, "instructionFollowing": null, "math": 50 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 6, "categoryRanks": { "agentic": 7, "instructionFollowing": 9 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "browseComp": 89.3 }, "coding": {}, "reasoning": { "arcAgi2": 83.3, "critpt": 30 }, "multimodalGrounded": { "mmmuPro": 94 }, "knowledge": { "hle": 58.7, "frontierScience": 36.7, "frontierScienceResearch": 36.7, "hleNoTools": 42.7 }, "multilingual": {}, "instructionFollowing": {}, "math": { "ipho2025Theory": 93.5, "frontierMath": 50 } } }, { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 89, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md", "id": 32, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-5", "familyName": "GPT-5.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-5", "relatedModelKeys": [ "gpt-5-5-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gpt-5-4" }, "scores": { "displayScore": 89, "overallScore": 88, "rawOverallScore": 88, "verifiedDisplayScore": 72, "displayCategoryScores": { "agentic": 95.9, "coding": 82.6, "reasoning": 96.3, "multimodalGrounded": 58, "knowledge": 95.6, "multilingual": null, "instructionFollowing": null, "math": 96.4 }, "verifiedDisplayCategoryScores": { "agentic": 81.5, "coding": 58.6, "reasoning": 85, "multimodalGrounded": 70.4, "knowledge": 66.4, "multilingual": null, "instructionFollowing": null, "math": 51.7 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 7, "categoryRanks": { "agentic": 4, "multimodalGrounded": 59 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 22, "verifiedBenchmarkCount": 22, "rankableBenchmarkCount": 23, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 82, "cyberGym": 81.8, "browseComp": 84.4, "osWorldVerified": 78.7, "mcpAtlas": 75.3, "toolathlon": 55.6, "tau2Bench": 93.9, "aaAgenticIndex": 74.12, "apexAgentsAa": 37.7, "gdpvalAaNormalized": 63.5, "gdpvalAa": 1769, "gertLabs": 72.93 }, "coding": { "swePro": 58.6, "terminalBench2": 82, "vibeCodeBench": 69.847, "reactNativeEvals": 84.7, "cursorBench31": 59.2, "aaCodingIndex": 59.12, "terminalBenchHard": 60.6, "aaSciCode": 56.1 }, "reasoning": { "mrcrv2_64_128": 83.1, "mrcrv2_128_256": 87.5, "arcAgi2": 85, "lcr": 74.3, "critpt": 27.1 }, "multimodalGrounded": { "mmmuPro": 81.2, "mmmuProPython": 83.2, "officeQaPro": 54.1, "aaMmmuPro": 79.9, "designArenaWebsite": 1297 }, "knowledge": { "gpqa": 93.6, "gpqaDiamond": 93.6, "hle": 52.2, "hleNoTools": 41.4, "artificialAnalysis": 60.24, "aaGpqaDiamond": 93.5, "aaHle": 44.3, "aaOmniscienceIndex": 20.1, "omniscienceAccuracy": 56.9, "omniscienceHallucinationRate": 85.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": { "frontierMath": 51.7 } } }, { "slug": "gemini-3-pro-deep-think", "canonicalModelKey": "gemini-3-pro-deep-think", "model": "Gemini 3 Pro Deep Think", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 89, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/gemini-3-pro-deep-think", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro-deep-think.md", "id": 12, "releaseDate": "2026-02-12", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-pro", "familyName": "Gemini 3 Pro", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-pro", "relatedModelKeys": [ "gemini-3-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 89, "overallScore": 87, "rawOverallScore": 87, "verifiedDisplayScore": 45, "displayCategoryScores": { "agentic": 93.9, "coding": 73.4, "reasoning": 88.5, "multimodalGrounded": 100, "knowledge": 86.7, "multilingual": 82.1, "instructionFollowing": 81.6, "math": 94.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 45.1, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 8, "categoryRanks": { "agentic": 6, "coding": 35, "reasoning": 6, "multimodalGrounded": 1, "knowledge": 9, "multilingual": 18, "instructionFollowing": 33, "math": 6 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "gdpvalAaNormalized": 41.2, "gdpvalAa": 1324 }, "coding": {}, "reasoning": { "arcAgi2": 45.1, "critpt": 25.7 }, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-4-1", "canonicalModelKey": "grok-4-1", "model": "Grok 4.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 89, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/grok-4-1", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1.md", "id": 7, "releaseDate": "2025-11-17", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1", "familyName": "Grok 4.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 89, "overallScore": 89, "rawOverallScore": 89, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 76.6, "coding": 81.7, "reasoning": 97.6, "multimodalGrounded": 97.8, "knowledge": 93.7, "multilingual": 96.9, "instructionFollowing": 90.6, "math": 99.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 9, "categoryRanks": { "agentic": 18, "coding": 20, "reasoning": 1, "multimodalGrounded": 3, "knowledge": 5, "multilingual": 6, "instructionFollowing": 19, "math": 2 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 37, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-4", "canonicalModelKey": "gpt-5-4", "model": "GPT-5.4", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 88, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md", "id": 11, "releaseDate": "2026-03-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4-pro", "gpt-5-4-mini", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 88, "overallScore": 88, "rawOverallScore": 88, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 84.5, "coding": 87.2, "reasoning": 95.6, "multimodalGrounded": 59.6, "knowledge": 98.5, "multilingual": 100, "instructionFollowing": 96, "math": 94.4 }, "verifiedDisplayCategoryScores": { "agentic": 77, "coding": 57.7, "reasoning": null, "multimodalGrounded": 72.7, "knowledge": 52.1, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 10, "categoryRanks": { "agentic": 11, "coding": 10, "reasoning": 3, "multimodalGrounded": 52, "knowledge": 3, "multilingual": 4, "instructionFollowing": 4, "math": 7 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 26, "verifiedBenchmarkCount": 26, "rankableBenchmarkCount": 63, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 75.1, "cyberGym": 79, "browseComp": 82.7, "osWorldVerified": 75, "mcpAtlas": 70.6, "toolathlon": 54.6, "tau2Bench": 87.1, "clawEval": 60.3, "deepSearchQa": 73.6, "aaAgenticIndex": 67.96, "apexAgentsAa": 33.3, "gdpvalAaNormalized": 58.7, "gdpvalAa": 1674, "gertLabs": 64.89 }, "coding": { "liveCodeBenchPro": 87.5, "swePro": 57.7, "reactNativeEvals": 85.3, "vibeCodeBench": 67.421, "aaCodingIndex": 57.25, "terminalBenchHard": 57.6, "aaSciCode": 56.6 }, "reasoning": { "lcr": 74, "critpt": 23.4 }, "multimodalGrounded": { "mmmuPro": 81.2, "officeQaPro": 53.2, "mmmuProPython": 82.1, "charxiv": 82.8, "erqa": 65.4, "simpleVqa": 61.1, "screenSpotPro": 85.4, "zeroBench": 41, "medXpertQaMm": 77.1, "gdpvalAa": 1672, "aaMmmuPro": 78.4, "designArenaWebsite": 1269 }, "knowledge": { "gpqa": 92.8, "hle": 52.1, "hleNoTools": 39.8, "gpqaDiamond": 92.8, "healthBenchHard": 40.1, "medXpertQaText": 59.6, "artificialAnalysis": 56.8, "aaGpqaDiamond": 92, "aaHle": 41.6, "aaOmniscienceIndex": 5.7, "omniscienceAccuracy": 50, "omniscienceHallucinationRate": 88.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.9 }, "math": {}, "korean": {} } }, { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 88, "rankingEligible": true, "overallRank": 11, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "id": 249, "releaseDate": "2026-06-03", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-7-plus", "familyName": "Qwen3.7 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-7-plus", "relatedModelKeys": [ "qwen3-7-max", "qwen3-6-plus", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "qwen3-6-plus" }, "scores": { "displayScore": 88, "overallScore": 86, "rawOverallScore": 86, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 85.3, "coding": 87.7, "reasoning": 100, "multimodalGrounded": 76, "knowledge": 79.2, "multilingual": 79.6, "instructionFollowing": 95.6, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 71.7, "coding": 71.1, "reasoning": 91.7, "multimodalGrounded": 81.1, "knowledge": 67.9, "multilingual": 85.4, "instructionFollowing": 89.2, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 11, "categoryRanks": { "coding": 9, "multimodalGrounded": 22, "knowledge": 20, "multilingual": 21, "instructionFollowing": 6 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 50, "verifiedBenchmarkCount": 50, "rankableBenchmarkCount": 50, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 70.3, "qwenClawBench": 61.8, "qwenWebBench": 1536, "clawEval": 62.7, "bfclV4": 72.9, "mcpAtlas": 73.2, "vitaBench": 45.6, "deepPlanning": 62.3, "osWorldVerified": 73.3, "androidWorld": 81, "aaAgenticIndex": 65.13, "apexAgentsAa": 22.4, "tau2Bench": 93, "gdpvalAaNormalized": 50.9, "gdpvalAa": 1518 }, "coding": { "terminalBench2": 70.3, "sweVerified": 77.7, "swePro": 57.6, "sweMultilingual": 75.8, "nl2Repo": 41.1, "sciCode": 51.3, "liveCodeBench": 89.6, "aaCodingIndex": 46.48, "terminalBenchHard": 47, "aaSciCode": 45.5 }, "reasoning": { "critpt": 9.1, "mrcrv2": 91.7, "lcr": 65 }, "multimodalGrounded": { "mmmuPro": 79, "mathVision": 90.3, "charxiv": 85.9, "erqa": 69.8, "medXpertQaMm": 71, "screenSpotPro": 79, "simpleVqa": 81.7, "mmSearchPlus": 41.4, "realWorldQa": 86.9, "omniDocBench15": 91.4, "ocrBenchV2": 70.7, "odinw13": 51.1, "videoMmeWithSub": 88, "videoMmmu": 85.4, "mlvuAvg": 87.4, "aaMmmuPro": 44.8 }, "knowledge": { "gpqa": 90.3, "gpqaDiamond": 90.3, "hle": 34.7, "mmluPro": 88.5, "mmluRedux": 94.5, "superGpqa": 71.4, "mmmlu": 89, "artificialAnalysis": 53.25, "aaGpqaDiamond": 90, "aaHle": 33.4, "aaOmniscienceIndex": 2.4, "omniscienceAccuracy": 22.2, "omniscienceHallucinationRate": 25.5 }, "multilingual": { "mmluProX": 85.4, "nova63": 58.8, "include": 83, "maxife": 88.8, "polyMath": 84 }, "instructionFollowing": { "ifeval": 94.6, "ifBench": 79.1, "aaIfBench": 78 }, "math": { "hmmtFeb2026": 92.9, "imoAnswerBench": 86, "apex": 22.7 } } }, { "slug": "claude-opus-4-6", "canonicalModelKey": "claude-opus-4-6", "model": "Claude Opus 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 86, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md", "id": 18, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-6", "familyName": "Claude Opus 4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 86, "overallScore": 86, "rawOverallScore": 86, "verifiedDisplayScore": 72, "displayCategoryScores": { "agentic": 81.3, "coding": 85.5, "reasoning": 88.2, "multimodalGrounded": 76.7, "knowledge": 90.1, "multilingual": 100, "instructionFollowing": 95.3, "math": 86.3 }, "verifiedDisplayCategoryScores": { "agentic": 72.6, "coding": 64.4, "reasoning": null, "multimodalGrounded": 77.3, "knowledge": 76.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 12, "categoryRanks": { "agentic": 14, "coding": 13, "reasoning": 8, "multimodalGrounded": 21, "knowledge": 8, "multilingual": 5, "instructionFollowing": 8, "math": 18 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 27, "verifiedBenchmarkCount": 27, "rankableBenchmarkCount": 73, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 65.4, "browseComp": 83.7, "osWorldVerified": 72.7, "tau2Bench": 84.8, "clawEval": 70.4, "deepSearchQa": 73.7, "cyberGym": 66.6, "aaAgenticIndex": 64.22, "gdpvalAaNormalized": 54.5, "gdpvalAa": 1589, "gertLabs": 61.85 }, "coding": { "sweVerified": 80.84, "sweVerifiedArcee": 75.6, "liveCodeBenchPro": 70.7, "swePro": 53.4, "sweRebench": 65.3, "reactNativeEvals": 84.1, "vibeCodeBench": 57.573, "aaCodingIndex": 47.56, "terminalBenchHard": 48.5, "aaSciCode": 45.7 }, "reasoning": { "lcr": 58.3, "critpt": 2.8 }, "multimodalGrounded": { "mmmuPro": 77.3, "erqa": 51.6, "screenSpotPro": 83.1, "medXpertQaMm": 64.8, "gdpvalAa": 1606, "aaMmmuPro": 72.5, "designArenaWebsite": 1340 }, "knowledge": { "gpqa": 91.3, "gpqaDiamond": 89.2, "superGpqa": 95, "mmluPro": 82, "mmluProArcee": 89.1, "hle": 53, "hleNoTools": 40, "healthBenchHard": 14.8, "medXpertQaText": 52.1, "artificialAnalysis": 46.46, "aaGpqaDiamond": 84, "aaHle": 18.6, "aaOmniscienceIndex": 3.5, "omniscienceAccuracy": 45.2, "omniscienceHallucinationRate": 76 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.6 }, "math": { "aime2025Arcee": 99.8 } } }, { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 86, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "id": 38, "releaseDate": "2026-05-19", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-5-flash", "familyName": "Gemini 3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-5-flash", "relatedModelKeys": [ "gemini-3-flash", "gemini-3-1-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gemini-3-flash" }, "scores": { "displayScore": 86, "overallScore": 83, "rawOverallScore": 83, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": 95.1, "coding": 77.3, "reasoning": 79.4, "multimodalGrounded": 80, "knowledge": 82, "multilingual": null, "instructionFollowing": 78, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 77.2, "coding": 54.5, "reasoning": 74.7, "multimodalGrounded": 83.8, "knowledge": 58, "multilingual": null, "instructionFollowing": 76.3, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 13, "categoryRanks": { "agentic": 5, "coding": 30, "reasoning": 17, "multimodalGrounded": 17, "instructionFollowing": 42 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 20, "verifiedBenchmarkCount": 20, "rankableBenchmarkCount": 21, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 76.2, "mcpAtlas": 83.6, "toolathlon": 56.5, "osWorldVerified": 78.4, "financeAgentV2": 57.861, "gdpvalAa": 1656, "tau2Bench": 95.3, "gdpvalAaNormalized": 57.8, "aaAgenticIndex": 70.3, "apexAgentsAa": 47.1, "gertLabs": 61.85 }, "coding": { "terminalBench2": 76.2, "terminalBenchHard": 40.9, "swePro": 55.1, "sciCode": 53.1, "vibeCodeBench": 48.683, "cursorBench31": 49.8, "aaCodingIndex": 44.98, "aaSciCode": 53.1 }, "reasoning": { "mrcrv2": 77.3, "mrcr1m": 26.6, "arcAgi2": 72.1, "lcr": 69.3, "critpt": 13.1 }, "multimodalGrounded": { "charxiv": 84.2, "mmmuPro": 83.6, "blueprintBench2": 33.6, "aaMmmuPro": 84.3, "designArenaWebsite": 1292 }, "knowledge": { "artificialAnalysis": 55.33, "gpqa": 92.2, "gpqaDiamond": 92.676, "hle": 40.2, "omniscienceAccuracy": 51.9, "omniscienceHallucinationRate": 60.7, "aaGpqaDiamond": 92.2, "aaHle": 41, "aaOmniscienceIndex": 22.7 }, "multilingual": {}, "instructionFollowing": { "ifBench": 76.3, "aaIfBench": 76.3 }, "math": {} } }, { "slug": "deepseek-v4-pro-max", "canonicalModelKey": "deepseek-v4-pro-max", "model": "DeepSeek V4 Pro (Max)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 86, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/deepseek-v4-pro-max", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-max.md", "id": 29, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "pro-reasoning", "snapshotLabel": "max", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-high" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 86, "overallScore": 85, "rawOverallScore": 85, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 87.7, "coding": 89.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 76.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 74, "coding": 75.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.1, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 14, "categoryRanks": { "coding": 8, "knowledge": 26 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 24, "verifiedBenchmarkCount": 24, "rankableBenchmarkCount": 25, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 67.9, "browseComp": 83.4, "hleWithTools": 48.2, "mcpAtlas": 73.6, "gdpvalAa": 1554, "toolathlon": 51.8, "aaAgenticIndex": 67.19, "apexAgentsAa": 24.3, "tau2Bench": 96.2, "gdpvalAaNormalized": 52.7 }, "coding": { "liveCodeBench": 93.5, "codeforces": 3206, "sweVerified": 80.6, "swePro": 55.4, "sweMultilingual": 76.2, "terminalBench2": 67.9, "vibeCodeBench": 49.931, "aaCodingIndex": 47.47, "terminalBenchHard": 46.2, "aaSciCode": 50 }, "reasoning": { "mrcr1m": 83.5, "corpusQa1m": 62, "lcr": 66.3, "critpt": 12.9 }, "multimodalGrounded": { "designArenaWebsite": 1286 }, "knowledge": { "mmluPro": 87.5, "simpleQa": 57.9, "chineseSimpleQa": 84.4, "gpqa": 90.1, "gpqaDiamond": 90.1, "hle": 37.7, "artificialAnalysis": 51.51, "aaGpqaDiamond": 88.8, "aaHle": 35.9, "aaOmniscienceIndex": -10, "omniscienceAccuracy": 43.3, "omniscienceHallucinationRate": 94 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.5 }, "math": { "hmmtFeb2026": 95.2, "imoAnswerBench": 89.8, "apex": 38.3, "apexShortlist": 90.2 } } }, { "slug": "gpt-5-3-codex", "canonicalModelKey": "gpt-5-3-codex", "model": "GPT-5.3 Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 85, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex.md", "id": 5, "releaseDate": "2026-02-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3-codex", "familyName": "GPT-5.3 Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-codex", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 85, "overallScore": 91, "rawOverallScore": 91, "verifiedDisplayScore": 67, "displayCategoryScores": { "agentic": 77.4, "coding": 87.1, "reasoning": 93, "multimodalGrounded": 95.8, "knowledge": 92, "multilingual": 96.9, "instructionFollowing": 91.4, "math": 100 }, "verifiedDisplayCategoryScores": { "agentic": 71.5, "coding": 63.1, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 15, "categoryRanks": { "agentic": 16, "coding": 11, "reasoning": 4, "multimodalGrounded": 5, "knowledge": 6, "multilingual": 7, "instructionFollowing": 18, "math": 1 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 39, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 77.3, "osWorldVerified": 64.7, "aaAgenticIndex": 60.54, "tau2Bench": 86, "gdpvalAaNormalized": 49, "gdpvalAa": 1480, "gertLabs": 57.47 }, "coding": { "sweVerified": 85, "swePro": 56.8, "sweRebench": 58.2, "vibeCodeBench": 61.767, "aaCodingIndex": 53.1, "terminalBenchHard": 53, "aaSciCode": 53.2 }, "reasoning": { "lcr": 74, "critpt": 16.9 }, "multimodalGrounded": { "aaMmmuPro": 78.5, "designArenaWebsite": 1208 }, "knowledge": { "artificialAnalysis": 53.56, "aaGpqaDiamond": 91.5, "aaHle": 39.9, "aaOmniscienceIndex": 9.9, "omniscienceAccuracy": 51.8, "omniscienceHallucinationRate": 86.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.4 }, "math": {} } }, { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 84, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md", "id": 33, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-7", "familyName": "Claude Opus 4.7", "variantType": "reasoning", "snapshotLabel": "adaptive", "baseFamilyModelKey": "claude-opus-4-7", "relatedModelKeys": [ "claude-opus-4-7", "claude-opus-4-6", "claude-opus-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "claude-opus-4-6" }, "scores": { "displayScore": 84, "overallScore": 84, "rawOverallScore": 84, "verifiedDisplayScore": 71, "displayCategoryScores": { "agentic": 86.2, "coding": 93.5, "reasoning": 90.7, "multimodalGrounded": 45, "knowledge": 99.6, "multilingual": null, "instructionFollowing": null, "math": 71.2 }, "verifiedDisplayCategoryScores": { "agentic": 74.9, "coding": 72.9, "reasoning": 75.8, "multimodalGrounded": 64.3, "knowledge": 68.2, "multilingual": null, "instructionFollowing": null, "math": 43.8 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 16, "categoryRanks": { "agentic": 9, "coding": 4, "multimodalGrounded": 73, "knowledge": 1 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 18, "verifiedBenchmarkCount": 18, "rankableBenchmarkCount": 19, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 69.4, "browseComp": 79.3, "mcpAtlas": 77.3, "osWorldVerified": 78, "cyberGym": 73.1, "aaAgenticIndex": 71.29, "tau2Bench": 88.6, "gdpvalAaNormalized": 62.6, "gdpvalAa": 1753 }, "coding": { "sweVerified": 87.6, "swePro": 64.3, "terminalBench2": 69.4, "aaCodingIndex": 52.51, "terminalBenchHard": 51.5, "aaSciCode": 54.5 }, "reasoning": { "mrcrv2_128_256": 59.2, "arcAgi2": 75.8, "lcr": 70.3, "critpt": 12 }, "multimodalGrounded": { "officeQaPro": 43.6, "charxiv": 91, "charxivNoTools": 82.1, "aaMmmuPro": 78.8, "designArenaWebsite": 1338 }, "knowledge": { "gpqa": 94.2, "gpqaDiamond": 94.2, "hle": 54.7, "hleNoTools": 46.9, "artificialAnalysis": 57.28, "aaGpqaDiamond": 91.4, "aaHle": 39.6, "aaOmniscienceIndex": 26.2, "omniscienceAccuracy": 45.8, "omniscienceHallucinationRate": 36.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 58.6 }, "math": { "frontierMath": 43.8 } } }, { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 82, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md", "id": 43, "releaseDate": "2026-04-07", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "snapshot", "snapshotLabel": "5.1", "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning", "glm-5-turbo" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "glm-5" }, "scores": { "displayScore": 82, "overallScore": 75, "rawOverallScore": 75, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 79.7, "coding": 82.8, "reasoning": 64.8, "multimodalGrounded": null, "knowledge": 83.9, "multilingual": null, "instructionFollowing": 92, "math": 89.2 }, "verifiedDisplayCategoryScores": { "agentic": 65.3, "coding": 60.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 52.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 17, "categoryRanks": { "coding": 16, "reasoning": 31, "knowledge": 11, "instructionFollowing": 14, "math": 15 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": true, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 63.5, "browseComp": 68, "tau3Bench": 70.6, "mcpAtlas": 71.8, "cyberGym": 68.7, "clawEval": 62.3, "aaAgenticIndex": 67.05, "tau2Bench": 97.7, "gdpvalAaNormalized": 51.8, "gertLabs": 60.11 }, "coding": { "swePro": 58.4, "nl2Repo": 42.7, "sweRebench": 62.7, "vibeCodeBench": 31.456, "aaCodingIndex": 43.37, "terminalBenchHard": 43.2, "aaSciCode": 43.8 }, "reasoning": { "lcr": 62.3, "critpt": 4.6 }, "multimodalGrounded": { "designArenaWebsite": 1315 }, "knowledge": { "gpqaDiamond": 86.2, "hle": 52.3, "artificialAnalysis": 51.41, "aaGpqaDiamond": 86.8, "aaHle": 28, "aaOmniscienceIndex": 1.9, "omniscienceAccuracy": 24.2, "omniscienceHallucinationRate": 29.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.3 }, "math": { "aime2026": 95.3, "hmmtNov2025": 94, "hmmtFeb2026": 82.6, "mmAnswerBench": 83.8 } } }, { "slug": "claude-sonnet-4-6", "canonicalModelKey": "claude-sonnet-4-6", "model": "Claude Sonnet 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 82, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md", "id": 27, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-6", "familyName": "Claude Sonnet 4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-sonnet-4-6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 82, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 78.7, "coding": 82, "reasoning": 82.9, "multimodalGrounded": 86.2, "knowledge": 81.9, "multilingual": 88.4, "instructionFollowing": 82.7, "math": 75.7 }, "verifiedDisplayCategoryScores": { "agentic": 65.1, "coding": 66.4, "reasoning": null, "multimodalGrounded": 77.4, "knowledge": 73.7, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 18, "categoryRanks": { "agentic": 15, "coding": 19, "reasoning": 13, "multimodalGrounded": 12, "knowledge": 15, "multilingual": 9, "instructionFollowing": 31, "math": 28 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 48, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 59.1, "osWorldVerified": 72.1, "clawEval": 67.8, "cyberGym": 65.2, "aaAgenticIndex": 61.62, "tau2Bench": 79.5, "gdpvalAaNormalized": 54.8, "gdpvalAa": 1596, "gertLabs": 62.92 }, "coding": { "sweVerified": 79.6, "sweRebench": 60.7, "reactNativeEvals": 80.6, "vibeCodeBench": 51.476, "cursorBench31": 48.8, "aaCodingIndex": 46.43, "terminalBenchHard": 46.2, "aaSciCode": 46.9 }, "reasoning": { "lcr": 57.7, "critpt": 0.9 }, "multimodalGrounded": { "charxiv": 77.4, "aaMmmuPro": 70.6, "designArenaWebsite": 1327 }, "knowledge": { "gpqa": 89.9, "superGpqa": 95, "mmluPro": 79.2, "hle": 49, "artificialAnalysis": 44.38, "aaGpqaDiamond": 79.9, "aaHle": 13.2, "aaOmniscienceIndex": -2.9, "omniscienceAccuracy": 38, "omniscienceHallucinationRate": 65.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.2 }, "math": {}, "korean": {} } }, { "slug": "deepseek-v4-pro-high", "canonicalModelKey": "deepseek-v4-pro-high", "model": "DeepSeek V4 Pro (High)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82, "rankingEligible": true, "overallRank": 19, "url": "https://benchlm.ai/models/deepseek-v4-pro-high", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-high.md", "id": 45, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "pro-reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 82, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": 82, "coding": 86, "reasoning": null, "multimodalGrounded": null, "knowledge": 70.9, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 70, "coding": 73.8, "reasoning": null, "multimodalGrounded": null, "knowledge": 62.6, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 19, "categoryRanks": { "coding": 12, "knowledge": 36 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 63.3, "browseComp": 80.4, "hleWithTools": 44.7, "mcpAtlas": 74.2, "toolathlon": 49, "aaAgenticIndex": 66.65, "tau2Bench": 94.2, "gdpvalAaNormalized": 52.9, "gdpvalAa": 1558 }, "coding": { "liveCodeBench": 89.8, "codeforces": 2919, "sweVerified": 79.4, "swePro": 54.4, "sweMultilingual": 74.1, "terminalBench2": 63.3, "aaCodingIndex": 43.25, "terminalBenchHard": 41.7, "aaSciCode": 46.4 }, "reasoning": { "mrcr1m": 83.3, "corpusQa1m": 56.5, "lcr": 65, "critpt": 10 }, "multimodalGrounded": { "designArenaWebsite": 1286 }, "knowledge": { "mmluPro": 87.1, "simpleQa": 46.2, "chineseSimpleQa": 77.7, "gpqa": 89.1, "gpqaDiamond": 89.1, "hle": 34.5, "artificialAnalysis": 49.79, "aaGpqaDiamond": 90.5, "aaHle": 33.5, "aaOmniscienceIndex": -9.7, "omniscienceAccuracy": 41.8, "omniscienceHallucinationRate": 88.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.3 }, "math": { "hmmtFeb2026": 94, "imoAnswerBench": 88, "apex": 27.4, "apexShortlist": 85.5 } } }, { "slug": "o1-preview", "canonicalModelKey": "o1-preview", "model": "o1-preview", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 82, "rankingEligible": true, "overallRank": 20, "url": "https://benchlm.ai/models/o1-preview", "markdownUrl": "https://benchlm.ai/md/models/o1-preview.md", "id": 20, "releaseDate": "2024-09-12", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "snapshot", "snapshotLabel": "preview", "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1", "o1-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 82, "overallScore": 82, "rawOverallScore": 82, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 87.9, "coding": 78.8, "reasoning": 88.6, "multimodalGrounded": 67.5, "knowledge": 79.8, "multilingual": 82, "instructionFollowing": 76.9, "math": 94.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 20, "categoryRanks": { "agentic": 8, "coding": 23, "reasoning": 5, "multimodalGrounded": 34, "knowledge": 19, "multilingual": 19, "instructionFollowing": 43, "math": 8 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 34.05 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 23.74 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "kimi-2-6", "canonicalModelKey": "kimi-2-6", "model": "Kimi K2.6", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 81, "rankingEligible": true, "overallRank": 21, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "id": 44, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "kimi-2-6", "familyName": "Kimi K2.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-2-6", "relatedModelKeys": [ "kimi-k2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "kimi-k2-5" }, "scores": { "displayScore": 81, "overallScore": 81, "rawOverallScore": 81, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": 82.7, "coding": 89.8, "reasoning": null, "multimodalGrounded": 71.3, "knowledge": 73.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 73.1, "coding": 72, "reasoning": null, "multimodalGrounded": 79.7, "knowledge": 53.8, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 21, "categoryRanks": { "agentic": 12, "coding": 7, "multimodalGrounded": 29 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 28, "verifiedBenchmarkCount": 28, "rankableBenchmarkCount": 29, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 66.7, "browseComp": 83.2, "osWorldVerified": 73.1, "toolathlon": 50, "mcpAtlas": 55.9, "clawEval": 62.3, "deepSearchQa": 92.5, "wideResearch": 80.8, "aaAgenticIndex": 65.97, "tau2Bench": 95.9, "gdpvalAaNormalized": 49.1, "gdpvalAa": 1481, "apexAgentsAa": 28.5, "gertLabs": 56.82 }, "coding": { "sweVerified": 80.2, "liveCodeBench": 89.6, "liveCodeBenchV6": 89.6, "swePro": 58.6, "sweMultilingual": 76.7, "sciCode": 52.2, "terminalBench2": 66.7, "vibeCodeBench": 37.891, "cursorBench31": 47.6, "aaCodingIndex": 47.12, "terminalBenchHard": 43.9, "aaSciCode": 53.5 }, "reasoning": { "lcr": 69.7, "critpt": 8 }, "multimodalGrounded": { "mmmuPro": 79.4, "mmmuProPython": 80.1, "charxiv": 80.4, "mathVision": 87.4, "vStar": 96.9, "aaMmmuPro": 79.4, "designArenaWebsite": 1322 }, "knowledge": { "gpqa": 90.5, "gpqaDiamond": 90.5, "hle": 34.7, "artificialAnalysis": 53.9, "aaGpqaDiamond": 91.1, "aaHle": 35.9, "aaOmniscienceIndex": 6.4, "omniscienceAccuracy": 32.8, "omniscienceHallucinationRate": 39.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76 }, "math": { "aime2026": 96.4, "hmmtFeb2026": 92.7, "mmAnswerBench": 86 } } }, { "slug": "gemini-3-pro", "canonicalModelKey": "gemini-3-pro", "model": "Gemini 3 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 80, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md", "id": 34, "releaseDate": "2025-11-18", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-pro", "familyName": "Gemini 3 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-pro", "relatedModelKeys": [ "gemini-3-pro-deep-think" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 80, "overallScore": 74, "rawOverallScore": 74, "verifiedDisplayScore": 52, "displayCategoryScores": { "agentic": 70.6, "coding": 72.4, "reasoning": 82.4, "multimodalGrounded": 81.2, "knowledge": 82.3, "multilingual": 79.2, "instructionFollowing": 79.5, "math": 80.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 31.1, "multimodalGrounded": 81.1, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 22, "categoryRanks": { "agentic": 22, "coding": 37, "reasoning": 14, "multimodalGrounded": 16, "knowledge": 13, "multilingual": 22, "instructionFollowing": 39, "math": 23 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 63, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "aaAgenticIndex": 51.98, "tau2Bench": 87.1, "gdpvalAaNormalized": 34.2, "gdpvalAa": 1184, "gertLabs": 63.23 }, "coding": { "vibeCodeBench": 14.3, "aaCodingIndex": 46.49, "terminalBenchHard": 41.7, "aaSciCode": 56.1 }, "reasoning": { "arcAgi2": 31.1, "lcr": 70.7, "critpt": 9.1 }, "multimodalGrounded": { "mmmuPro": 81, "mathVision": 86.6, "videoMmmu": 87.6, "screenSpotPro": 72.7, "charxiv": 81.4, "vStar": 88, "aaMmmuPro": 80.2 }, "knowledge": { "artificialAnalysis": 48.39, "aaGpqaDiamond": 90.8, "aaHle": 37.2, "aaOmniscienceIndex": 15.8, "omniscienceAccuracy": 55.9, "omniscienceHallucinationRate": 90.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70.4 }, "math": {} } }, { "slug": "minimax-m3", "canonicalModelKey": "minimax-m3", "model": "MiniMax M3", "creator": "MiniMax", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 79, "rankingEligible": true, "overallRank": 23, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md", "id": 241, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m3", "familyName": "MiniMax M3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m3", "relatedModelKeys": [ "minimax-m2-7", "minimax-m2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "minimax-m2-7" }, "scores": { "displayScore": 79, "overallScore": 76, "rawOverallScore": 76, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 85.3, "coding": 84.6, "reasoning": null, "multimodalGrounded": 48.1, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 71.9, "coding": 67, "reasoning": null, "multimodalGrounded": 64.9, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 23, "categoryRanks": { "agentic": 10, "multimodalGrounded": 70 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 15, "verifiedBenchmarkCount": 15, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 66, "browseComp": 83.52, "osWorldVerified": 70.06, "mcpAtlas": 74.2, "clawEval": 74.5, "aaAgenticIndex": 68.62, "tau2Bench": 88.9, "gdpvalAaNormalized": 58.5, "gdpvalAa": 1670, "gdpvalRubrics": 74.7, "bankerToolBench": 76.1 }, "coding": { "sweVerified": 80.5, "swePro": 59, "terminalBench2": 66, "nl2Repo": 42.13, "aaCodingIndex": 43.41, "terminalBenchHard": 42.4, "aaSciCode": 45.4, "vibeV2": 50.1, "svgBench": 63.7, "kernelBenchHard": 28.8 }, "reasoning": { "lcr": 74, "critpt": 3.7 }, "multimodalGrounded": { "officeQaPro": 45.1, "omniDocBench15": 91.6, "mmmuPro": 78.1, "videoMmmu": 84.6, "videoMmeWithSub": 85.4, "aaMmmuPro": 79.9, "designArenaWebsite": 1312 }, "knowledge": { "artificialAnalysis": 54.67, "aaGpqaDiamond": 92.9, "aaHle": 37.1, "aaOmniscienceIndex": 1.4, "omniscienceAccuracy": 15, "omniscienceHallucinationRate": 16.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 82.9 }, "math": { "usamo2026": 85.71 } } }, { "slug": "glm-5-reasoning", "canonicalModelKey": "glm-5-reasoning", "model": "GLM-5 (Reasoning)", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 79, "rankingEligible": true, "overallRank": 24, "url": "https://benchlm.ai/models/glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/glm-5-reasoning.md", "id": 22, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 79, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 77, "coding": 69.1, "reasoning": 87.4, "multimodalGrounded": 72.6, "knowledge": 81.4, "multilingual": 79.2, "instructionFollowing": 81, "math": 92.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 24, "categoryRanks": { "agentic": 17, "coding": 41, "reasoning": 11, "multimodalGrounded": 26, "knowledge": 17, "multilingual": 23, "instructionFollowing": 35, "math": 11 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 41, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 23.359 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1292 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-2", "canonicalModelKey": "gpt-5-2", "model": "GPT-5.2", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 78, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md", "id": 26, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2-instant", "gpt-5-2-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 78, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 59.2, "coding": 78.7, "reasoning": 83.5, "multimodalGrounded": 81.5, "knowledge": 91.1, "multilingual": 95.9, "instructionFollowing": 84.9, "math": 80.9 }, "verifiedDisplayCategoryScores": { "agentic": 55.2, "coding": 64.7, "reasoning": 52.9, "multimodalGrounded": 80.3, "knowledge": 92.4, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 25, "categoryRanks": { "agentic": 31, "coding": 24, "reasoning": 12, "multimodalGrounded": 15, "knowledge": 7, "multilingual": 8, "instructionFollowing": 25, "math": 22 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 57, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "browseComp": 65.8, "osWorldVerified": 47.3, "aaAgenticIndex": 60.2, "tau2Bench": 84.8, "gdpvalAaNormalized": 48.3, "gdpvalAa": 1467, "gertLabs": 46.54 }, "coding": { "sweVerified": 80, "swePro": 55.6, "vibeCodeBench": 53.499, "aaCodingIndex": 48.67, "terminalBenchHard": 47, "aaSciCode": 52.1 }, "reasoning": { "arcAgi2": 52.9, "lcr": 72.7, "critpt": 11.6 }, "multimodalGrounded": { "mmmuPro": 79.5, "mathVision": 83, "charxiv": 82.1, "vStar": 75.9, "designArenaWebsite": 1240 }, "knowledge": { "gpqa": 92.4, "artificialAnalysis": 51.28, "aaGpqaDiamond": 90.3, "aaHle": 35.4, "aaOmniscienceIndex": -1, "omniscienceAccuracy": 43.8, "omniscienceHallucinationRate": 79.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.4 }, "math": {}, "korean": {} } }, { "slug": "qwen3-5-397b-reasoning", "canonicalModelKey": "qwen3-5-397b-reasoning", "model": "Qwen3.5 397B (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 77, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/qwen3-5-397b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b-reasoning.md", "id": 28, "releaseDate": "2026-02-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-397b", "familyName": "Qwen3.5 397B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-397b", "relatedModelKeys": [ "qwen3-5-397b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 77, "overallScore": 77, "rawOverallScore": 77, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 68.8, "coding": 85.4, "reasoning": 81.7, "multimodalGrounded": 58.4, "knowledge": 78, "multilingual": 82.9, "instructionFollowing": 80.6, "math": 92.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 26, "categoryRanks": { "agentic": 23, "reasoning": 15, "multimodalGrounded": 56, "knowledge": 23, "multilingual": 15, "instructionFollowing": 37, "math": 10 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 55.83, "apexAgentsAa": 15.3, "tau2Bench": 95.6, "gdpvalAaNormalized": 34.5, "gdpvalAa": 1190 }, "coding": { "aaCodingIndex": 41.28, "terminalBenchHard": 40.9, "aaSciCode": 42 }, "reasoning": { "lcr": 65.7, "critpt": 1.7 }, "multimodalGrounded": { "aaMmmuPro": 77.3 }, "knowledge": { "artificialAnalysis": 45.05, "aaGpqaDiamond": 89.3, "aaHle": 27.3, "aaOmniscienceIndex": -29.8, "omniscienceAccuracy": 31.4, "omniscienceHallucinationRate": 89.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 78.8 }, "math": {} } }, { "slug": "gpt-5-1", "canonicalModelKey": "gpt-5-1", "model": "GPT-5.1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 77, "rankingEligible": true, "overallRank": 27, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md", "id": 23, "releaseDate": "2025-11-13", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1", "familyName": "GPT-5.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 77, "overallScore": 81, "rawOverallScore": 81, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 74.1, "coding": 76, "reasoning": 66.7, "multimodalGrounded": 96.3, "knowledge": 81.5, "multilingual": 82.8, "instructionFollowing": 75.8, "math": 68.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 27, "categoryRanks": { "agentic": 20, "coding": 32, "reasoning": 29, "multimodalGrounded": 4, "knowledge": 16, "multilingual": 16, "instructionFollowing": 48, "math": 36 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 38, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 51.26, "tau2Bench": 81.9, "gdpvalAaNormalized": 36.4, "gdpvalAa": 1227, "gertLabs": 41.24 }, "coding": { "vibeCodeBench": 24.606, "aaCodingIndex": 44.73, "terminalBenchHard": 45.5, "aaSciCode": 43.3 }, "reasoning": { "lcr": 75, "critpt": 4.9 }, "multimodalGrounded": { "aaMmmuPro": 75.5, "designArenaWebsite": 1233 }, "knowledge": { "artificialAnalysis": 47.7, "aaGpqaDiamond": 87.3, "aaHle": 26.5, "aaOmniscienceIndex": 5.6, "omniscienceAccuracy": 37.6, "omniscienceHallucinationRate": 51.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 72.9 }, "math": {}, "korean": {} } }, { "slug": "claude-opus-4-5", "canonicalModelKey": "claude-opus-4-5", "model": "Claude Opus 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 76, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "id": 36, "releaseDate": "2025-11-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-5", "familyName": "Claude Opus 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 76, "overallScore": 72, "rawOverallScore": 72, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 73.5, "coding": 75.6, "reasoning": 69.6, "multimodalGrounded": 61.2, "knowledge": 83, "multilingual": 81.4, "instructionFollowing": 63.2, "math": 94.9 }, "verifiedDisplayCategoryScores": { "agentic": 62.5, "coding": 65.9, "reasoning": 64.4, "multimodalGrounded": 70, "knowledge": 66.2, "multilingual": 85.7, "instructionFollowing": 79.4, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 28, "categoryRanks": { "agentic": 21, "coding": 34, "reasoning": 25, "multimodalGrounded": 51, "knowledge": 12, "multilingual": 20, "instructionFollowing": 63, "math": 5 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 41, "verifiedBenchmarkCount": 41, "rankableBenchmarkCount": 82, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 59.3, "osWorldVerified": 66.3, "osWorld": 66.3, "clawEval": 59.6, "qwenClawBench": 52.3, "tau3Bench": 70.2, "vitaBench": 23.3, "deepPlanning": 26.4, "toolathlon": 43.5, "mcpAtlas": 42.3, "mcpTasks": 71.8, "wideResearch": 76.4, "cyberGym": 50.6, "aaAgenticIndex": 59.22, "tau2Bench": 86.3, "gdpvalAaNormalized": 45.9, "gdpvalAa": 1418, "gertLabs": 64.23 }, "coding": { "sweVerified": 80.9, "liveCodeBenchV6": 84.8, "swePro": 57.1, "sweMultilingual": 77.5, "nl2Repo": 43.2, "aaCodingIndex": 42.94, "terminalBenchHard": 40.9, "aaSciCode": 47 }, "reasoning": { "longBenchV2": 64.4, "aiNeedle": 74, "lcr": 65.3, "critpt": 0.3 }, "multimodalGrounded": { "mmmuPro": 70.6, "mathVision": 74.3, "charxiv": 68.5, "videoMmmu": 84.4, "screenSpotPro": 45.7, "vStar": 67, "aaMmmuPro": 71.2, "designArenaWebsite": 1292 }, "knowledge": { "gpqa": 87, "superGpqa": 70.6, "mmluPro": 89.5, "mmluRedux": 96.6, "cEval": 92.2, "hle": 30.8, "artificialAnalysis": 43.09, "aaGpqaDiamond": 81, "aaHle": 12.9, "aaOmniscienceIndex": -3.9, "omniscienceAccuracy": 40.7, "omniscienceHallucinationRate": 75.4 }, "multilingual": { "mmluProX": 85.7, "nova63": 56.7 }, "instructionFollowing": { "ifeval": 90.9, "ifBench": 58, "aaIfBench": 43 }, "math": { "aime2026": 95.1, "hmmtFeb2025": 92.9, "hmmtNov2025": 93.3, "hmmtFeb2026": 85.3, "mmAnswerBench": 84 } } }, { "slug": "gpt-5-high", "canonicalModelKey": "gpt-5-high", "model": "GPT-5 (high)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 76, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/gpt-5-high", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-high.md", "id": 19, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-medium", "gpt-5-mini", "gpt-5-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 76, "overallScore": 83, "rawOverallScore": 83, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 74.8, "coding": 69.7, "reasoning": 76.3, "multimodalGrounded": 93.3, "knowledge": 78.9, "multilingual": 79.2, "instructionFollowing": 80.7, "math": 70.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 29, "categoryRanks": { "agentic": 19, "coding": 40, "reasoning": 19, "multimodalGrounded": 7, "knowledge": 21, "multilingual": 24, "instructionFollowing": 36, "math": 35 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 37, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 54.65, "tau2Bench": 84.8, "gdpvalAaNormalized": 39.6, "gdpvalAa": 1292 }, "coding": { "vibeCodeBench": 20.088, "aaCodingIndex": 36.03, "terminalBenchHard": 32.6, "aaSciCode": 42.9 }, "reasoning": { "lcr": 75.6, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 74.2, "designArenaWebsite": 1230 }, "knowledge": { "artificialAnalysis": 44.63, "aaGpqaDiamond": 85.4, "aaHle": 26.5, "aaOmniscienceIndex": -8.1, "omniscienceAccuracy": 40.7, "omniscienceHallucinationRate": 82.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.1 }, "math": {} } }, { "slug": "gpt-5-2-codex", "canonicalModelKey": "gpt-5-2-codex", "model": "GPT-5.2-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 76, "rankingEligible": true, "overallRank": 30, "url": "https://benchlm.ai/models/gpt-5-2-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-codex.md", "id": 4, "releaseDate": "2025-12-18", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2-codex", "familyName": "GPT-5.2-Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2-codex", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 76, "overallScore": 90, "rawOverallScore": 90, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 77.5, "coding": 77.5, "reasoning": 87.8, "multimodalGrounded": 89, "knowledge": 77.4, "multilingual": 84.8, "instructionFollowing": 91.6, "math": 97.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 30, "categoryRanks": { "coding": 29, "reasoning": 10, "multimodalGrounded": 11, "knowledge": 25, "multilingual": 11, "instructionFollowing": 16, "math": 3 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 31, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 56.52, "tau2Bench": 92.1, "gdpvalAaNormalized": 39.4, "gdpvalAa": 1288, "gertLabs": 51.79 }, "coding": { "vibeCodeBench": 37.912, "aaCodingIndex": 42.96, "terminalBenchHard": 37.1, "aaSciCode": 54.6 }, "reasoning": { "lcr": 75.7, "critpt": 8.7 }, "multimodalGrounded": { "aaMmmuPro": 76.3 }, "knowledge": { "artificialAnalysis": 49.03, "aaGpqaDiamond": 89.9, "aaHle": 33.5, "aaOmniscienceIndex": -2.5, "omniscienceAccuracy": 40.7, "omniscienceHallucinationRate": 72.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 77.6 }, "math": {} } }, { "slug": "kimi-k2-5-reasoning", "canonicalModelKey": "kimi-k2-5-reasoning", "model": "Kimi K2.5 (Reasoning)", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 75, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5-reasoning.md", "id": 35, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-5", "familyName": "Kimi K2.5", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-5", "relatedModelKeys": [ "kimi-k2-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 75, "overallScore": 72, "rawOverallScore": 72, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 62, "coding": 85, "reasoning": 69.2, "multimodalGrounded": 67.8, "knowledge": 74, "multilingual": 87.8, "instructionFollowing": 98.9, "math": 67.2 }, "verifiedDisplayCategoryScores": { "agentic": 54.6, "coding": 76.8, "reasoning": null, "multimodalGrounded": 78.5, "knowledge": 87.3, "multilingual": null, "instructionFollowing": null, "math": 96.1 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 31, "categoryRanks": { "agentic": 25, "coding": 14, "reasoning": 26, "multimodalGrounded": 32, "knowledge": 30, "multilingual": 10, "instructionFollowing": 3, "math": 38 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 39, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 50.8, "browseComp": 60.6, "aaAgenticIndex": 58.94, "apexAgentsAa": 11.5, "tau2Bench": 95.9, "gdpvalAaNormalized": 39.2, "gdpvalAa": 1284, "gertLabs": 32.58 }, "coding": { "sweVerified": 76.8, "vibeCodeBench": 17.536, "aaCodingIndex": 39.55, "terminalBenchHard": 34.8, "aaSciCode": 49 }, "reasoning": { "lcr": 65.3, "critpt": 3.1 }, "multimodalGrounded": { "mmmuPro": 78.5, "aaMmmuPro": 75.4, "designArenaWebsite": 1294 }, "knowledge": { "gpqa": 87.6, "mmluPro": 87.1, "artificialAnalysis": 46.81, "aaGpqaDiamond": 87.9, "aaHle": 29.4, "aaOmniscienceIndex": -8.1, "omniscienceAccuracy": 34.3, "omniscienceHallucinationRate": 64.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70.2 }, "math": { "aime2025": 96.1 } } }, { "slug": "gpt-5-1-codex-max", "canonicalModelKey": "gpt-5-1-codex-max", "model": "GPT-5.1-Codex-Max", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 75, "rankingEligible": true, "overallRank": 32, "url": "https://benchlm.ai/models/gpt-5-1-codex-max", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex-max.md", "id": 1, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1-codex-max", "familyName": "GPT-5.1-Codex-Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1-codex-max", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 75, "overallScore": 90, "rawOverallScore": 90, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 75.5, "coding": 75.2, "reasoning": 88.4, "multimodalGrounded": 90.1, "knowledge": 78.2, "multilingual": 82.8, "instructionFollowing": 87.9, "math": 97.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 32, "categoryRanks": { "reasoning": 7, "multimodalGrounded": 9, "knowledge": 22, "multilingual": 17, "instructionFollowing": 21, "math": 4 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 30, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 50.68, "tau2Bench": 83, "gdpvalAaNormalized": 34.5, "gdpvalAa": 1191 }, "coding": { "vibeCodeBench": 22.168, "aaCodingIndex": 36.62, "terminalBenchHard": 34.8, "aaSciCode": 40.2 }, "reasoning": { "lcr": 67.3, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 72.5 }, "knowledge": { "artificialAnalysis": 43.11, "aaGpqaDiamond": 86, "aaHle": 23.4, "aaOmniscienceIndex": -6, "omniscienceAccuracy": 39.2, "omniscienceHallucinationRate": 74.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70 }, "math": {} } }, { "slug": "deepseek-v4-flash-max", "canonicalModelKey": "deepseek-v4-flash-max", "model": "DeepSeek V4 Flash (Max)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 74, "rankingEligible": true, "overallRank": 33, "url": "https://benchlm.ai/models/deepseek-v4-flash-max", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-max.md", "id": 64, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "flash-reasoning", "snapshotLabel": "max", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-pro", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 74, "overallScore": 72, "rawOverallScore": 72, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 68.8, "coding": 82.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.8, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 63.3, "coding": 73.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 60, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 33, "categoryRanks": { "coding": 18, "knowledge": 39 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 56.9, "browseComp": 73.2, "hleWithTools": 45.1, "mcpAtlas": 69, "gdpvalAa": 1388, "toolathlon": 47.8, "aaAgenticIndex": 61.28, "tau2Bench": 95, "gdpvalAaNormalized": 44.4 }, "coding": { "liveCodeBench": 91.6, "codeforces": 3052, "sweVerified": 79, "swePro": 52.6, "sweMultilingual": 73.3, "terminalBench2": 56.9, "aaCodingIndex": 38.71, "terminalBenchHard": 35.6, "aaSciCode": 44.9 }, "reasoning": { "mrcr1m": 78.7, "corpusQa1m": 60.5, "lcr": 63, "critpt": 7.1 }, "multimodalGrounded": { "designArenaWebsite": 1259 }, "knowledge": { "mmluPro": 86.2, "simpleQa": 34.1, "chineseSimpleQa": 78.9, "gpqa": 88.1, "gpqaDiamond": 88.1, "hle": 34.8, "artificialAnalysis": 46.52, "aaGpqaDiamond": 89.4, "aaHle": 32.1, "aaOmniscienceIndex": -22.9, "omniscienceAccuracy": 37.2, "omniscienceHallucinationRate": 95.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 79.2 }, "math": { "hmmtFeb2026": 94.8, "imoAnswerBench": 88.4, "apex": 33, "apexShortlist": 85.7 } } }, { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 72, "rankingEligible": true, "overallRank": 34, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md", "id": 63, "releaseDate": "2026-04-21", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-27b", "familyName": "Qwen3.6-27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-27b", "relatedModelKeys": [ "qwen3-6-35b-a3b", "qwen3-5-27b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 72, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 69.5, "coding": 77.9, "reasoning": null, "multimodalGrounded": 65, "knowledge": 68.7, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 59.3, "coding": 70.6, "reasoning": null, "multimodalGrounded": 76.6, "knowledge": 62.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 34, "categoryRanks": { "coding": 26, "multimodalGrounded": 43, "knowledge": 38 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 37, "verifiedBenchmarkCount": 37, "rankableBenchmarkCount": 37, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 59.3, "clawEval": 72.4, "qwenClawBench": 53.4, "qwenWebBench": 1487, "androidWorld": 70.3, "aaAgenticIndex": 62.85, "tau2Bench": 94.2, "gdpvalAaNormalized": 45.2, "gdpvalAa": 1403, "gertLabs": 54.84 }, "coding": { "sweVerified": 77.2, "sweMultilingual": 71.3, "swePro": 53.5, "terminalBench2": 59.3, "liveCodeBench": 83.9, "nl2Repo": 36.2, "aaCodingIndex": 36.5, "terminalBenchHard": 34.8, "aaSciCode": 39.8 }, "reasoning": { "lcr": 68.7, "critpt": 1.1 }, "multimodalGrounded": { "mmmu": 82.9, "mmmuPro": 75.8, "realWorldQa": 84.1, "dynaMath": 85.6, "mStar": 81.4, "simpleVqa": 56.1, "charxiv": 78.4, "ccOcr": 81.2, "countBench": 97.8, "refcocoAvg": 92.5, "erqa": 62.5, "videoMmeWithSub": 87.7, "videoMmmu": 84.4, "mlvuAvg": 86.6, "vStar": 94.7, "aaMmmuPro": 74.6 }, "knowledge": { "mmluPro": 86.2, "mmluRedux": 93.5, "superGpqa": 66, "cEval": 91.4, "gpqa": 87.8, "hle": 24, "artificialAnalysis": 45.82, "aaGpqaDiamond": 84.2, "aaHle": 21.6, "aaOmniscienceIndex": -19.8, "omniscienceAccuracy": 19.2, "omniscienceHallucinationRate": 48.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.6 }, "math": { "hmmtFeb2025": 93.8, "hmmtNov2025": 90.7, "hmmtFeb2026": 84.3, "mmAnswerBench": 80.8, "aime2026": 94.1 } } }, { "slug": "grok-4-20-beta", "canonicalModelKey": "grok-4-20-beta", "model": "Grok 4.20", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 71, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md", "id": 85, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-20", "familyName": "Grok 4.20", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-20-beta", "relatedModelKeys": [ "grok-4-20-multi-agent-beta" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "grok-4-1" }, "scores": { "displayScore": 71, "overallScore": 60, "rawOverallScore": 60, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 54.5, "coding": 76.4, "reasoning": 64.7, "multimodalGrounded": 47.6, "knowledge": null, "multilingual": null, "instructionFollowing": 95.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 47.1, "coding": 61, "reasoning": 53.3, "multimodalGrounded": 70.8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 35, "categoryRanks": { "multimodalGrounded": 71, "instructionFollowing": 7 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 18, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 47.1, "deepSearchQa": 62.8, "gertLabs": 38.36 }, "coding": { "liveCodeBenchPro": 74.2, "sweVerified": 76.7, "swePro": 51.8, "vibeCodeBench": 4.064 }, "reasoning": { "arcAgi2": 53.3 }, "multimodalGrounded": { "mmmuPro": 75.2, "charxiv": 60.9, "erqa": 54.1, "simpleVqa": 57.4, "medXpertQaMm": 65.8, "gdpvalAa": 1055 }, "knowledge": { "gpqaDiamond": 88.5, "hleNoTools": 31.6, "healthBenchHard": 20.3, "medXpertQaText": 50.2 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-v4-flash-high", "canonicalModelKey": "deepseek-v4-flash-high", "model": "DeepSeek V4 Flash (High)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/deepseek-v4-flash-high", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-high.md", "id": 83, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "flash-reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 71, "overallScore": 65, "rawOverallScore": 65, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": 60.6, "coding": 82.5, "reasoning": null, "multimodalGrounded": null, "knowledge": 62.1, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 55.4, "coding": 72.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 57.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 36, "categoryRanks": { "coding": 17, "knowledge": 50 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 56.6, "browseComp": 53.5, "hleWithTools": 40.3, "mcpAtlas": 67.4, "toolathlon": 43.5, "aaAgenticIndex": 62.33, "tau2Bench": 95.6, "gdpvalAaNormalized": 45.7, "gdpvalAa": 1414 }, "coding": { "liveCodeBench": 88.4, "codeforces": 2816, "sweVerified": 78.6, "swePro": 52.3, "sweMultilingual": 70.2, "terminalBench2": 56.6, "aaCodingIndex": 39.76, "terminalBenchHard": 38.6, "aaSciCode": 42 }, "reasoning": { "mrcr1m": 76.9, "corpusQa1m": 59.3, "lcr": 62.7, "critpt": 3.4 }, "multimodalGrounded": { "designArenaWebsite": 1259 }, "knowledge": { "mmluPro": 86.4, "simpleQa": 28.9, "chineseSimpleQa": 73.2, "gpqa": 87.4, "gpqaDiamond": 87.4, "hle": 29.4, "artificialAnalysis": 46, "aaGpqaDiamond": 86.7, "aaHle": 27.8, "aaOmniscienceIndex": -22.3, "omniscienceAccuracy": 35.5, "omniscienceHallucinationRate": 89.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.5 }, "math": { "hmmtFeb2026": 91.9, "imoAnswerBench": 85.1, "apex": 19.1, "apexShortlist": 72.1 } } }, { "slug": "gpt-5-medium", "canonicalModelKey": "gpt-5-medium", "model": "GPT-5 (medium)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 70, "rankingEligible": true, "overallRank": 37, "url": "https://benchlm.ai/models/gpt-5-medium", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-medium.md", "id": 16, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "reasoning", "snapshotLabel": "medium", "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-mini", "gpt-5-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 70, "overallScore": 84, "rawOverallScore": 84, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 68.1, "coding": 77.7, "reasoning": 74.1, "multimodalGrounded": 90.6, "knowledge": 73.3, "multilingual": 83.8, "instructionFollowing": 76.9, "math": 91.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 37, "categoryRanks": { "agentic": 24, "coding": 27, "reasoning": 21, "multimodalGrounded": 8, "knowledge": 33, "multilingual": 14, "instructionFollowing": 44, "math": 12 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 45.83, "tau2Bench": 86.5, "gdpvalAaNormalized": 25.1, "gdpvalAa": 1001 }, "coding": { "aaCodingIndex": 38.95, "terminalBenchHard": 37.9, "aaSciCode": 41.1 }, "reasoning": { "lcr": 72.8, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 74.3, "designArenaWebsite": 1230 }, "knowledge": { "artificialAnalysis": 42.03, "aaGpqaDiamond": 84.2, "aaHle": 23.5, "aaOmniscienceIndex": -10.1, "omniscienceAccuracy": 38.9, "omniscienceHallucinationRate": 80.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70.6 }, "math": {} } }, { "slug": "nemotron-3-ultra", "canonicalModelKey": "nemotron-3-ultra-500b", "model": "Nemotron 3 Ultra", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 68, "rankingEligible": true, "overallRank": 38, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "id": 71, "releaseDate": "2026-06-04", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-ultra-500b", "familyName": "Nemotron 3 Ultra", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-ultra-500b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 65, "displayCategoryScores": { "agentic": 51, "coding": 80.4, "reasoning": 44, "multimodalGrounded": null, "knowledge": 73.8, "multilingual": 72.8, "instructionFollowing": 96, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 51.7, "coding": 74.2, "reasoning": 61.9, "multimodalGrounded": null, "knowledge": 62.6, "multilingual": 83, "instructionFollowing": 81.7, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 38, "categoryRanks": { "coding": 22, "knowledge": 31, "multilingual": 27, "instructionFollowing": 5 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 18, "verifiedBenchmarkCount": 18, "rankableBenchmarkCount": 18, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 56.4, "pinchBench": 90, "browseComp": 44.4, "tau3Bench": 70.9, "gdpvalAaNormalized": 44, "hleWithTools": 37.4, "aaAgenticIndex": 57.06, "tau2Bench": 83.3, "gdpvalAa": 1379 }, "coding": { "sweVerified": 71.9, "sweMultilingual": 67.7, "liveCodeBench": 89, "sciCode": 44.6, "terminalBench2": 56.4, "aaCodingIndex": 37.55, "terminalBenchHard": 36.4, "aaSciCode": 39.9 }, "reasoning": { "lcr": 67, "critpt": 3.1, "longBenchV2": 61.9 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 87, "gpqaDiamond": 87, "hle": 26.7, "hleNoTools": 26.7, "mmluPro": 86.8, "omniscienceAccuracy": 21.6, "artificialAnalysis": 47.67, "aaGpqaDiamond": 86.7, "aaHle": 26.6, "aaOmniscienceIndex": -0.8, "omniscienceHallucinationRate": 28.5 }, "multilingual": { "mmluProX": 83 }, "instructionFollowing": { "ifBench": 81.7, "aaIfBench": 81.4 }, "math": {} } }, { "slug": "deepseek-v4-pro", "canonicalModelKey": "deepseek-v4-pro", "model": "DeepSeek V4 Pro", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 68, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/deepseek-v4-pro", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro.md", "id": 104, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "pro", "snapshotLabel": "non-think", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 60, "rawOverallScore": 60, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 66.5, "coding": 68.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 50.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 59.1, "coding": 58.8, "reasoning": null, "multimodalGrounded": null, "knowledge": 49.4, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 39, "categoryRanks": { "coding": 43, "knowledge": 60 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 22, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 59.1, "mcpAtlas": 69.4, "toolathlon": 46.3, "clawEval": 59.8, "gertLabs": 50.28 }, "coding": { "liveCodeBench": 56.8, "sweVerified": 73.6, "swePro": 52.1, "sweMultilingual": 69.8, "terminalBench2": 59.1 }, "reasoning": { "mrcr1m": 44.7, "corpusQa1m": 35.6 }, "multimodalGrounded": { "designArenaWebsite": 1286 }, "knowledge": { "mmluPro": 82.9, "simpleQa": 45, "chineseSimpleQa": 75.8, "gpqa": 72.9, "gpqaDiamond": 72.9, "hle": 7.7 }, "multilingual": {}, "instructionFollowing": {}, "math": { "hmmtFeb2026": 31.7, "imoAnswerBench": 35.3, "apex": 0.4, "apexShortlist": 9.2 } } }, { "slug": "glm-4-7", "canonicalModelKey": "glm-4-7", "model": "GLM-4.7", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 68, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/glm-4-7", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7.md", "id": 48, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-7", "familyName": "GLM-4.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 66, "rawOverallScore": 66, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": 53.5, "coding": 72.5, "reasoning": 72.9, "multimodalGrounded": 58.2, "knowledge": 66.3, "multilingual": 71.3, "instructionFollowing": 72.9, "math": 78.2 }, "verifiedDisplayCategoryScores": { "agentic": 45.3, "coding": 70.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 24.8, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 40, "categoryRanks": { "agentic": 41, "coding": 36, "reasoning": 22, "multimodalGrounded": 58, "knowledge": 42, "multilingual": 30, "instructionFollowing": 50, "math": 25 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 41, "browseComp": 52, "vitaBench": 15.5, "aaAgenticIndex": 55.01, "tau2Bench": 95.9, "gdpvalAaNormalized": 34.1, "gdpvalAa": 1183, "gertLabs": 39.95 }, "coding": { "sweVerified": 73.8, "liveCodeBench": 84.9, "sweRebench": 58.7, "aaCodingIndex": 36.26, "terminalBenchHard": 31.8, "aaSciCode": 45.1 }, "reasoning": { "lcr": 64, "critpt": 1.7 }, "multimodalGrounded": { "designArenaWebsite": 1272 }, "knowledge": { "gpqa": 85.7, "mmluPro": 84.3, "hle": 24.8, "artificialAnalysis": 42.11, "aaGpqaDiamond": 85.9, "aaHle": 25.1, "aaOmniscienceIndex": -34.6, "omniscienceAccuracy": 29.3, "omniscienceHallucinationRate": 90.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.9 }, "math": { "aime2025": 95.7 } } }, { "slug": "grok-4-1-fast", "canonicalModelKey": "grok-4-1-fast", "model": "Grok 4.1 Fast", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 68, "rankingEligible": true, "overallRank": 41, "url": "https://benchlm.ai/models/grok-4-1-fast", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast.md", "id": 21, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1-fast", "familyName": "Grok 4.1 Fast", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-1-fast", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 61.4, "coding": 59.8, "reasoning": 87.9, "multimodalGrounded": 89.7, "knowledge": 75.1, "multilingual": 74.6, "instructionFollowing": 79.7, "math": 93.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 41, "categoryRanks": { "agentic": 28, "coding": 49, "reasoning": 9, "multimodalGrounded": 10, "knowledge": 29, "multilingual": 26, "instructionFollowing": 38, "math": 9 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 36, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 32.95, "tau2Bench": 63.7, "gdpvalAaNormalized": 14.1, "gdpvalAa": 781, "gertLabs": 47.32 }, "coding": { "aaCodingIndex": 19.47, "terminalBenchHard": 14.4, "aaSciCode": 29.6 }, "reasoning": { "lcr": 22, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 48.4 }, "knowledge": { "artificialAnalysis": 23.56, "aaGpqaDiamond": 63.7, "aaHle": 5, "aaOmniscienceIndex": -50.9, "omniscienceAccuracy": 17, "omniscienceHallucinationRate": 81.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.5 }, "math": {} } }, { "slug": "glm-5", "canonicalModelKey": "glm-5", "model": "GLM-5", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 67, "rankingEligible": true, "overallRank": 42, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "id": 51, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 67, "overallScore": 67, "rawOverallScore": 67, "verifiedDisplayScore": 65, "displayCategoryScores": { "agentic": 48.4, "coding": 76.2, "reasoning": 60.5, "multimodalGrounded": 56, "knowledge": 82.2, "multilingual": 70.9, "instructionFollowing": 84.3, "math": 91.3 }, "verifiedDisplayCategoryScores": { "agentic": 56.2, "coding": 63.2, "reasoning": 60.8, "multimodalGrounded": null, "knowledge": 70.7, "multilingual": 83.1, "instructionFollowing": 92.6, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 42, "categoryRanks": { "agentic": 48, "coding": 31, "reasoning": 33, "multimodalGrounded": 61, "knowledge": 14, "multilingual": 31, "instructionFollowing": 28, "math": 13 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 33, "verifiedBenchmarkCount": 33, "rankableBenchmarkCount": 73, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 56.2, "clawEval": 57.7, "qwenClawBench": 54.1, "tau3Bench": 65.6, "deepPlanning": 14.6, "toolathlon": 38, "mcpAtlas": 31.1, "mcpTasks": 60.8, "wideResearch": 69.8, "tau2Bench": 98.2, "cyberGym": 43.2, "aaAgenticIndex": 63.14, "apexAgentsAa": 14.5, "gdpvalAaNormalized": 44.6, "gdpvalAa": 1391, "gertLabs": 50.99 }, "coding": { "sweVerified": 77.8, "sweVerifiedArcee": 72.8, "swePro": 55.1, "sweMultilingual": 73.3, "sweRebench": 62.8, "reactNativeEvals": 74.8, "aaCodingIndex": 44.18, "terminalBenchHard": 43.2, "aaSciCode": 46.2 }, "reasoning": { "longBenchV2": 60.8, "aiNeedle": 63.3, "lcr": 63.3, "critpt": 2 }, "multimodalGrounded": { "designArenaWebsite": 1292 }, "knowledge": { "gpqa": 86, "gpqaDiamond": 86, "superGpqa": 66.8, "mmluPro": 85.7, "mmluProArcee": 85.8, "hle": 50.4, "artificialAnalysis": 49.77, "aaGpqaDiamond": 82, "aaHle": 27.2, "aaOmniscienceIndex": 2, "omniscienceAccuracy": 26.9, "omniscienceHallucinationRate": 34 }, "multilingual": { "mmluProX": 83.1, "nova63": 55.1 }, "instructionFollowing": { "ifeval": 92.6, "aaIfBench": 72.3 }, "math": { "aime2026": 95.8, "aime2025Arcee": 93.3, "hmmtFeb2025": 97.5, "hmmtNov2025": 96.9, "hmmtFeb2026": 86.4, "mmAnswerBench": 82.5 } } }, { "slug": "qwen3-6-plus", "canonicalModelKey": "qwen3-6-plus", "model": "Qwen3.6 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 66, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "id": 55, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-plus", "familyName": "Qwen3.6 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-plus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 66, "overallScore": 66, "rawOverallScore": 66, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 55.9, "coding": 77.7, "reasoning": 44.2, "multimodalGrounded": 71.6, "knowledge": 75.7, "multilingual": 77.6, "instructionFollowing": 91.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 61.6, "coding": 64.8, "reasoning": 62, "multimodalGrounded": 79.6, "knowledge": 66, "multilingual": 84.7, "instructionFollowing": 87.8, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 43, "categoryRanks": { "agentic": 36, "coding": 28, "multimodalGrounded": 28, "knowledge": 27, "multilingual": 25, "instructionFollowing": 15 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 38, "verifiedBenchmarkCount": 38, "rankableBenchmarkCount": 69, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 61.6, "clawEval": 58.8, "qwenClawBench": 57.2, "tau3Bench": 70.7, "vitaBench": 44.3, "deepPlanning": 41.5, "toolathlon": 39.8, "mcpAtlas": 48.2, "mcpTasks": 74.1, "wideResearch": 74.3, "aaAgenticIndex": 61.67, "tau2Bench": 97.7, "gdpvalAaNormalized": 42.5, "gdpvalAa": 1350, "gertLabs": 50.6 }, "coding": { "sweVerified": 78.8, "swePro": 56.6, "sweMultilingual": 73.8, "liveCodeBenchV6": 87.1, "vibeCodeBench": 25.564, "aaCodingIndex": 42.87, "terminalBenchHard": 43.9, "aaSciCode": 40.7 }, "reasoning": { "aiNeedle": 68.3, "longBenchV2": 62, "lcr": 69.7, "critpt": 2.9 }, "multimodalGrounded": { "mmmu": 86, "mmmuPro": 78.8, "mathVision": 88, "videoMmmu": 84, "screenSpotPro": 68.2, "charxiv": 81.5, "vStar": 96.9, "aaMmmuPro": 78, "designArenaWebsite": 1264 }, "knowledge": { "gpqa": 90.4, "superGpqa": 71.6, "mmluPro": 88.5, "mmluRedux": 94.5, "cEval": 93.3, "hle": 28.8, "artificialAnalysis": 49.98, "aaGpqaDiamond": 88.2, "aaHle": 25.7, "aaOmniscienceIndex": 2.7, "omniscienceAccuracy": 26.2, "omniscienceHallucinationRate": 32 }, "multilingual": { "mmluProX": 84.7, "nova63": 57.9 }, "instructionFollowing": { "ifeval": 94.3, "ifBench": 75.8, "aaIfBench": 75.2 }, "math": { "aime2026": 95.3, "hmmtFeb2025": 96.7, "hmmtNov2025": 94.6, "hmmtFeb2026": 87.8, "mmAnswerBench": 83.8 } } }, { "slug": "mai-thinking-1", "canonicalModelKey": "mai-thinking-1", "model": "MAI-Thinking-1", "creator": "Microsoft", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 65, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md", "id": 250, "releaseDate": "2026-06-02", "market": null, "isRegional": false, "family": { "familyKey": "mai-thinking", "familyName": "MAI-Thinking", "variantType": "1", "snapshotLabel": null, "baseFamilyModelKey": "mai-thinking-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 65, "overallScore": 65, "rawOverallScore": 65, "verifiedDisplayScore": 65, "displayCategoryScores": { "agentic": 31.9, "coding": 84.5, "reasoning": null, "multimodalGrounded": null, "knowledge": 64.6, "multilingual": null, "instructionFollowing": 100, "math": 98.4 }, "verifiedDisplayCategoryScores": { "agentic": 46, "coding": 71, "reasoning": null, "multimodalGrounded": null, "knowledge": 69.9, "multilingual": null, "instructionFollowing": 85, "math": 97 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 44, "categoryRanks": { "coding": 15, "knowledge": 47, "instructionFollowing": 1 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 46 }, "coding": { "liveCodeBench": 87.7, "sweVerified": 73.5, "swePro": 52.8, "terminalBench2": 46 }, "reasoning": { "graphwalksBfs128k": 90 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 84.2, "gpqaDiamond": 84.2, "mmluPro": 85, "simpleQa": 31 }, "multilingual": {}, "instructionFollowing": { "ifBench": 85 }, "math": { "aime2025": 97, "aime2026": 94.5, "hmmtFeb2026": 84.9 } } }, { "slug": "qwen3-6-35b-a3b", "canonicalModelKey": "qwen3-6-35b-a3b", "model": "Qwen3.6-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 65, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md", "id": 76, "releaseDate": "2026-04-15", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-35b-a3b", "familyName": "Qwen3.6-35B-A3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-35b-a3b", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-5-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 65, "overallScore": 62, "rawOverallScore": 62, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": 53.7, "coding": 72.2, "reasoning": null, "multimodalGrounded": 64, "knowledge": 65.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 51.5, "coding": 66.9, "reasoning": null, "multimodalGrounded": 76.1, "knowledge": 60.5, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 45, "categoryRanks": { "coding": 38, "multimodalGrounded": 45, "knowledge": 43 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 40, "verifiedBenchmarkCount": 40, "rankableBenchmarkCount": 40, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 51.5, "clawEval": 68.7, "qwenClawBench": 52.6, "qwenWebBench": 1397, "tau3Bench": 67.2, "vitaBench": 35.6, "deepPlanning": 25.9, "toolathlon": 26.9, "mcpAtlas": 62.8, "wideResearch": 60.1, "aaAgenticIndex": 58.34, "tau2Bench": 95.3, "gdpvalAaNormalized": 39.9, "gdpvalAa": 1298, "gertLabs": 42.65 }, "coding": { "sweVerified": 73.4, "sweMultilingual": 67.2, "swePro": 49.5, "terminalBench2": 51.5, "liveCodeBench": 80.4, "nl2Repo": 29.4, "aaCodingIndex": 35.15, "terminalBenchHard": 34.8, "aaSciCode": 35.8 }, "reasoning": { "lcr": 63.7, "critpt": 0.3 }, "multimodalGrounded": { "mmmu": 81.7, "mmmuPro": 75.3, "realWorldQa": 85.3, "omniDocBench15": 89.9, "charxiv": 78, "simpleVqa": 58.9, "ccOcr": 81.9, "ai2dTest": 92.7, "refcocoAvg": 92, "odinw13": 50.8, "videoMmeWithSub": 86.6, "videoMmeNoSub": 82.5, "videoMmmu": 83.7, "mlvuAvg": 86.2, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 85.2, "superGpqa": 64.7, "cEval": 90, "gpqa": 86, "hle": 21.4, "artificialAnalysis": 43.49, "aaGpqaDiamond": 84.1, "aaHle": 20.2, "aaOmniscienceIndex": -21.4, "omniscienceAccuracy": 18.9, "omniscienceHallucinationRate": 49.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 64.4 }, "math": { "hmmtFeb2025": 90.7, "hmmtNov2025": 89.1, "hmmtFeb2026": 83.6, "mmAnswerBench": 78.9, "aime2026": 92.7 } } }, { "slug": "claude-sonnet-4-5", "canonicalModelKey": "claude-sonnet-4-5", "model": "Claude Sonnet 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 64, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5.md", "id": 31, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-5", "familyName": "Claude Sonnet 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-sonnet-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 64, "overallScore": 75, "rawOverallScore": 75, "verifiedDisplayScore": 56, "displayCategoryScores": { "agentic": 54, "coding": 78.4, "reasoning": 62, "multimodalGrounded": 94.8, "knowledge": 73.7, "multilingual": 84.8, "instructionFollowing": 84.2, "math": 87.7 }, "verifiedDisplayCategoryScores": { "agentic": 55.3, "coding": 77.2, "reasoning": 13.6, "multimodalGrounded": null, "knowledge": 83.4, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 46, "categoryRanks": { "agentic": 40, "coding": 25, "reasoning": 32, "multimodalGrounded": 6, "knowledge": 32, "multilingual": 12, "instructionFollowing": 29, "math": 16 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 38, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 50, "osWorldVerified": 61.4, "vitaBench": 17, "gertLabs": 48.51 }, "coding": { "sweVerified": 77.2 }, "reasoning": { "arcAgi2": 13.6 }, "multimodalGrounded": { "designArenaWebsite": 1235 }, "knowledge": { "gpqa": 83.4 }, "multilingual": {}, "instructionFollowing": {}, "math": { "aime2025": 87 } } }, { "slug": "kimi-k2-5", "canonicalModelKey": "kimi-k2-5", "model": "Kimi K2.5", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 63, "rankingEligible": true, "overallRank": 47, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "id": 53, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-5", "familyName": "Kimi K2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-5", "relatedModelKeys": [ "kimi-k2-5-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 45, "coding": 81, "reasoning": 54.6, "multimodalGrounded": 63.1, "knowledge": 70.6, "multilingual": 68.4, "instructionFollowing": 84.5, "math": 56.8 }, "verifiedDisplayCategoryScores": { "agentic": 54.6, "coding": 64.2, "reasoning": 61, "multimodalGrounded": 78.5, "knowledge": 65.1, "multilingual": 82.3, "instructionFollowing": 93.9, "math": 96.1 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 47, "categoryRanks": { "agentic": 50, "coding": 21, "reasoning": 49, "multimodalGrounded": 48, "knowledge": 37, "multilingual": 35, "instructionFollowing": 27, "math": 43 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 39, "verifiedBenchmarkCount": 39, "rankableBenchmarkCount": 108, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 50.8, "browseComp": 60.6, "clawEval": 52.3, "qwenClawBench": 54.3, "tau3Bench": 65.7, "deepSearchQa": 77.1, "deepPlanning": 14.4, "toolathlon": 27.8, "mcpAtlas": 29.5, "mcpTasks": 59.1, "wideResearch": 72.7, "tau2Bench": 95.9, "aaAgenticIndex": 58.94, "apexAgentsAa": 11.5, "gdpvalAaNormalized": 39.2, "gdpvalAa": 1284, "gertLabs": 45.88 }, "coding": { "sweVerified": 76.8, "sweVerifiedArcee": 70.8, "liveCodeBench": 85, "liveCodeBenchV6": 85, "swePro": 50.7, "sweMultilingual": 73, "sweRebench": 58.5, "reactNativeEvals": 77.2, "sciCode": 48.7, "aaCodingIndex": 39.55, "terminalBenchHard": 34.8, "aaSciCode": 49 }, "reasoning": { "longBenchV2": 61, "lcr": 65.3, "critpt": 3.1 }, "multimodalGrounded": { "mmmuPro": 78.5, "videoMme": 87.4, "mmvu": 80.4, "videoMmmu": 86.6, "aaMmmuPro": 75.4, "designArenaWebsite": 1294 }, "knowledge": { "gpqa": 87.6, "gpqaDiamond": 87.6, "superGpqa": 69.2, "mmluPro": 87.1, "mmluProArcee": 87.1, "hle": 30.1, "artificialAnalysis": 46.81, "aaGpqaDiamond": 87.9, "aaHle": 29.4, "aaOmniscienceIndex": -8.1, "omniscienceAccuracy": 34.3, "omniscienceHallucinationRate": 64.6 }, "multilingual": { "mmluProX": 82.3, "nova63": 56 }, "instructionFollowing": { "ifeval": 93.9, "aaIfBench": 70.2 }, "math": { "aime2025": 96.1, "aime2026": 95.8, "aime2025Arcee": 96.3, "hmmtFeb2025": 95.4, "hmmtNov2025": 91.1, "hmmtFeb2026": 87.1, "mmAnswerBench": 81.8 } } }, { "slug": "qwen3-5-122b-a10b", "canonicalModelKey": "qwen3-5-122b-a10b", "model": "Qwen3.5-122B-A10B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 63, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "id": 37, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-122b-a10b", "familyName": "Qwen3.5-122B-A10B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-122b-a10b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 66, "rawOverallScore": 66, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": 55.4, "coding": 70.7, "reasoning": 39, "multimodalGrounded": 65.2, "knowledge": 80.2, "multilingual": 70.6, "instructionFollowing": 87.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 56.1, "coding": 72, "reasoning": 60.2, "multimodalGrounded": 77.2, "knowledge": 81.6, "multilingual": 82.2, "instructionFollowing": 93.4, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 48, "categoryRanks": { "agentic": 37, "multimodalGrounded": 40, "knowledge": 18, "multilingual": 32, "instructionFollowing": 22 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 19, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 49.4, "browseComp": 63.8, "osWorldVerified": 58, "tau2Bench": 93.6, "aaAgenticIndex": 53, "gdpvalAaNormalized": 30.7, "gdpvalAa": 1115 }, "coding": { "sweVerified": 72, "aaCodingIndex": 34.71, "terminalBenchHard": 31.1, "aaSciCode": 42 }, "reasoning": { "longBenchV2": 60.2, "lcr": 66.7, "critpt": 0.6 }, "multimodalGrounded": { "mmmu": 83.9, "mmvu": 74.7, "mathVision": 86.2, "charxiv": 77.2, "vStar": 93.2, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 86.7, "superGpqa": 67.1, "gpqa": 86.6, "artificialAnalysis": 41.6, "aaGpqaDiamond": 85.7, "aaHle": 23.4, "aaOmniscienceIndex": -39.6, "omniscienceAccuracy": 24.7, "omniscienceHallucinationRate": 85.5 }, "multilingual": { "mmluProX": 82.2 }, "instructionFollowing": { "ifeval": 93.4, "aaIfBench": 75.7 }, "math": {} } }, { "slug": "gemini-2-5-pro", "canonicalModelKey": "gemini-2-5-pro", "model": "Gemini 2.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 63, "rankingEligible": true, "overallRank": 49, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md", "id": 68, "releaseDate": "2025-03-01", "market": null, "isRegional": false, "family": { "familyKey": "gemini-2-5-pro", "familyName": "Gemini 2.5 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-2-5-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 47, "displayCategoryScores": { "agentic": 57.5, "coding": 48.5, "reasoning": 59, "multimodalGrounded": 85.2, "knowledge": 64.9, "multilingual": 68.9, "instructionFollowing": 59, "math": 73.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 63.8, "reasoning": null, "multimodalGrounded": null, "knowledge": 18.8, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 49, "categoryRanks": { "agentic": 32, "coding": 61, "reasoning": 37, "multimodalGrounded": 13, "knowledge": 46, "multilingual": 34, "instructionFollowing": 71, "math": 30 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 38, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 32.68, "tau2Bench": 54.1, "gdpvalAaNormalized": 20.9, "gdpvalAa": 918, "gertLabs": 42.01 }, "coding": { "sweVerified": 63.8, "vibeCodeBench": 0.4, "aaCodingIndex": 31.95, "terminalBenchHard": 26.5, "aaSciCode": 42.8 }, "reasoning": { "lcr": 66, "critpt": 2.6 }, "multimodalGrounded": { "aaMmmuPro": 74.9, "designArenaWebsite": 1212 }, "knowledge": { "gpqa": 83, "hle": 18.8, "artificialAnalysis": 34.63, "aaGpqaDiamond": 84.4, "aaHle": 21.1, "aaOmniscienceIndex": -14.3, "omniscienceAccuracy": 39, "omniscienceHallucinationRate": 87.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.7 }, "math": {} } }, { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 63, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md", "id": 56, "releaseDate": "2025-07-09", "market": null, "isRegional": false, "family": { "familyKey": "grok-4", "familyName": "Grok 4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 64, "rawOverallScore": 64, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 53.1, "coding": 76, "reasoning": 55.2, "multimodalGrounded": 73, "knowledge": 65.2, "multilingual": 63.4, "instructionFollowing": 54.9, "math": 80 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 50, "categoryRanks": { "agentic": 44, "coding": 33, "reasoning": 45, "multimodalGrounded": 25, "knowledge": 45, "multilingual": 45, "instructionFollowing": 77, "math": 24 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 41.5, "tau2Bench": 74.9, "gdpvalAaNormalized": 24.6, "gdpvalAa": 991, "gertLabs": 42.34 }, "coding": { "reactNativeEvals": 72.6, "aaCodingIndex": 40.49, "terminalBenchHard": 37.9, "aaSciCode": 45.7 }, "reasoning": { "lcr": 68, "critpt": 2 }, "multimodalGrounded": { "aaMmmuPro": 68.8 }, "knowledge": { "artificialAnalysis": 41.52, "aaGpqaDiamond": 87.7, "aaHle": 23.9, "aaOmniscienceIndex": 3.8, "omniscienceAccuracy": 41.4, "omniscienceHallucinationRate": 64.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 53.7 }, "math": {} } }, { "slug": "qwen3-5-397b", "canonicalModelKey": "qwen3-5-397b", "model": "Qwen3.5 397B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 62, "rankingEligible": true, "overallRank": 51, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "id": 57, "releaseDate": "2026-02-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-397b", "familyName": "Qwen3.5 397B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-397b", "relatedModelKeys": [ "qwen3-5-397b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 62, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 53.5, "coding": 67.5, "reasoning": 58.4, "multimodalGrounded": 65.1, "knowledge": 71.4, "multilingual": 71.8, "instructionFollowing": 84.8, "math": 73.3 }, "verifiedDisplayCategoryScores": { "agentic": 56.2, "coding": 60.3, "reasoning": 63.2, "multimodalGrounded": 79.6, "knowledge": 65.2, "multilingual": 84.7, "instructionFollowing": 92.6, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 51, "categoryRanks": { "agentic": 42, "coding": 44, "reasoning": 40, "multimodalGrounded": 41, "knowledge": 35, "multilingual": 28, "instructionFollowing": 26, "math": 31 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 36, "verifiedBenchmarkCount": 36, "rankableBenchmarkCount": 86, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 52.5, "browseComp": 62, "clawEval": 56.8, "qwenClawBench": 51.8, "tau3Bench": 68.4, "vitaBench": 43.7, "deepPlanning": 37.6, "toolathlon": 36.3, "mcpAtlas": 46.1, "mcpTasks": 74.2, "wideResearch": 74, "aaAgenticIndex": 53.32, "tau2Bench": 83.9, "gdpvalAaNormalized": 35.8, "gdpvalAa": 1217, "gertLabs": 46.76 }, "coding": { "sweVerified": 76.2, "liveCodeBenchV6": 83.6, "swePro": 50.9, "aaCodingIndex": 37.43, "terminalBenchHard": 35.6, "aaSciCode": 41.1 }, "reasoning": { "longBenchV2": 63.2, "aiNeedle": 68.7, "lcr": 58, "critpt": 0.9 }, "multimodalGrounded": { "mmmuPro": 79, "mathVision": 88.6, "charxiv": 80.8, "videoMmmu": 84.7, "screenSpotPro": 65.6, "vStar": 95.8, "aaMmmuPro": 52.7 }, "knowledge": { "gpqa": 88.4, "superGpqa": 70.4, "mmluPro": 87.8, "mmluRedux": 94.9, "cEval": 93, "hle": 28.7, "artificialAnalysis": 40.1, "aaGpqaDiamond": 86.1, "aaHle": 18.8, "aaOmniscienceIndex": -36.1, "omniscienceAccuracy": 24.3, "omniscienceHallucinationRate": 79.8 }, "multilingual": { "mmluProX": 84.7, "nova63": 59.1 }, "instructionFollowing": { "ifeval": 92.6, "aaIfBench": 51.6 }, "math": { "aime2026": 93.3, "hmmtFeb2025": 94.8, "hmmtNov2025": 92.7, "hmmtFeb2026": 87.9, "mmAnswerBench": 80.9 } } }, { "slug": "qwen3-5-27b", "canonicalModelKey": "qwen3-5-27b", "model": "Qwen3.5-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61, "rankingEligible": true, "overallRank": 52, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "id": 47, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-27b", "familyName": "Qwen3.5-27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-27b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 61, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 50.2, "coding": 70.3, "reasoning": 39.1, "multimodalGrounded": 65.1, "knowledge": 78, "multilingual": 70.6, "instructionFollowing": 89, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 51.6, "coding": 63, "reasoning": 60.6, "multimodalGrounded": null, "knowledge": 80.6, "multilingual": 82.2, "instructionFollowing": 95, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 52, "categoryRanks": { "agentic": 45, "coding": 39, "multimodalGrounded": 42, "knowledge": 24, "multilingual": 33, "instructionFollowing": 20 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 20, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 41.6, "browseComp": 61, "osWorldVerified": 56.2, "tau2Bench": 93.9, "aaAgenticIndex": 54.61, "gdpvalAaNormalized": 33, "gdpvalAa": 1160, "gertLabs": 39.41 }, "coding": { "sweVerified": 72.4, "sweRebench": 58.9, "aaCodingIndex": 34.87, "terminalBenchHard": 32.6, "aaSciCode": 39.5 }, "reasoning": { "longBenchV2": 60.6, "lcr": 67.3, "critpt": 0.9 }, "multimodalGrounded": { "mmmu": 82.3, "mmvu": 73.3, "mathVision": 86, "vStar": 93.7, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 86.1, "superGpqa": 65.6, "gpqa": 85.5, "artificialAnalysis": 42.07, "aaGpqaDiamond": 85.8, "aaHle": 22.2, "aaOmniscienceIndex": -42, "omniscienceAccuracy": 21, "omniscienceHallucinationRate": 79.7 }, "multilingual": { "mmluProX": 82.2 }, "instructionFollowing": { "ifeval": 95, "aaIfBench": 75.6 }, "math": {} } }, { "slug": "deepseek-v3-2-thinking", "canonicalModelKey": "deepseek-v3-2-thinking", "model": "DeepSeek V3.2 (Thinking)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 60, "rankingEligible": true, "overallRank": 53, "url": "https://benchlm.ai/models/deepseek-v3-2-thinking", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2-thinking.md", "id": 72, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-2", "familyName": "DeepSeek V3.2", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-2", "relatedModelKeys": [ "deepseek-v3-2" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 60, "overallScore": 59, "rawOverallScore": 59, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 61.5, "coding": 51.5, "reasoning": 55, "multimodalGrounded": 59, "knowledge": 66.7, "multilingual": 63.4, "instructionFollowing": 62.1, "math": 51.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 53, "categoryRanks": { "agentic": 27, "coding": 57, "reasoning": 47, "multimodalGrounded": 53, "knowledge": 40, "multilingual": 46, "instructionFollowing": 67, "math": 50 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 42, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 5.108 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1222 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mimo-v2-flash", "canonicalModelKey": "mimo-v2-flash", "model": "MiMo-V2-Flash", "creator": "Xiaomi", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 59, "rankingEligible": true, "overallRank": 54, "url": "https://benchlm.ai/models/mimo-v2-flash", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-flash.md", "id": 42, "releaseDate": "2026-03-15", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-flash", "familyName": "MiMo-V2-Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-flash", "relatedModelKeys": [ "mimo-v2-pro", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 59, "overallScore": 66, "rawOverallScore": 66, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 57.1, "coding": 68.6, "reasoning": 55.6, "multimodalGrounded": 68.7, "knowledge": 63.3, "multilingual": 58.8, "instructionFollowing": 62.3, "math": 82.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 73.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 54, "categoryRanks": { "agentic": 33, "coding": 42, "reasoning": 44, "multimodalGrounded": 31, "knowledge": 48, "multilingual": 55, "instructionFollowing": 64, "math": 20 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 47.34, "tau2Bench": 83.9, "gdpvalAaNormalized": 28, "gdpvalAa": 1059 }, "coding": { "sweVerified": 73.4, "aaCodingIndex": 25.81, "terminalBenchHard": 25.8, "aaSciCode": 25.9 }, "reasoning": { "lcr": 31.3, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1212 }, "knowledge": { "gpqa": 83.7, "mmluPro": 84.9, "artificialAnalysis": 30.35, "aaGpqaDiamond": 65.6, "aaHle": 8, "aaOmniscienceIndex": -48.5, "omniscienceAccuracy": 15.2, "omniscienceHallucinationRate": 75.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.9 }, "math": { "aime2025": 94.1 } } }, { "slug": "deepseek-v4-flash", "canonicalModelKey": "deepseek-v4-flash", "model": "DeepSeek V4 Flash", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 57, "rankingEligible": true, "overallRank": 55, "url": "https://benchlm.ai/models/deepseek-v4-flash", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash.md", "id": 122, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "flash", "snapshotLabel": "non-think", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-pro-base", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": 51, "displayCategoryScores": { "agentic": 47.7, "coding": 62, "reasoning": null, "multimodalGrounded": null, "knowledge": 44.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 49.1, "coding": 57.1, "reasoning": null, "multimodalGrounded": null, "knowledge": 45.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 55, "categoryRanks": { "coding": 46, "knowledge": 68 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 22, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 49.1, "mcpAtlas": 64, "toolathlon": 40.7, "clawEval": 57.8, "gertLabs": 54.35 }, "coding": { "liveCodeBench": 55.2, "sweVerified": 73.7, "swePro": 49.1, "sweMultilingual": 69.7, "terminalBench2": 49.1 }, "reasoning": { "mrcr1m": 37.5, "corpusQa1m": 15.5 }, "multimodalGrounded": { "designArenaWebsite": 1259 }, "knowledge": { "mmluPro": 83, "simpleQa": 23.1, "chineseSimpleQa": 71.5, "gpqa": 71.2, "gpqaDiamond": 71.2, "hle": 8.1 }, "multilingual": {}, "instructionFollowing": {}, "math": { "hmmtFeb2026": 40.8, "imoAnswerBench": 41.9, "apex": 1, "apexShortlist": 9.3 } } }, { "slug": "gpt-4-1", "canonicalModelKey": "gpt-4-1", "model": "GPT-4.1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 57, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/gpt-4-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1.md", "id": 59, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1-mini", "gpt-4-1-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gpt-4o" }, "scores": { "displayScore": 57, "overallScore": 64, "rawOverallScore": 64, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": 55.4, "coding": 54.6, "reasoning": 76.4, "multimodalGrounded": 63.9, "knowledge": 51.5, "multilingual": 33.6, "instructionFollowing": 74.7, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 54.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.3, "multilingual": null, "instructionFollowing": 87.4, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 56, "categoryRanks": { "agentic": 38, "reasoning": 18, "multimodalGrounded": 46, "multilingual": 75, "instructionFollowing": 49 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 27.26, "tau2Bench": 47.1, "gdpvalAaNormalized": 13.8, "gdpvalAa": 777, "gertLabs": 25.65 }, "coding": { "sweVerified": 54.6, "aaCodingIndex": 21.78, "terminalBenchHard": 13.6, "aaSciCode": 38.1 }, "reasoning": { "lcr": 61, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 61.2, "designArenaWebsite": 1084 }, "knowledge": { "mmlu": 90.2, "gpqa": 66.3, "artificialAnalysis": 26.28, "aaGpqaDiamond": 66.6, "aaHle": 4.6, "aaOmniscienceIndex": -36.2, "omniscienceAccuracy": 24.2, "omniscienceHallucinationRate": 79.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 87.4, "aaIfBench": 43 }, "math": {}, "korean": {} } }, { "slug": "o3-pro", "canonicalModelKey": "o3-pro", "model": "o3-pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 57, "rankingEligible": true, "overallRank": 57, "url": "https://benchlm.ai/models/o3-pro", "markdownUrl": "https://benchlm.ai/md/models/o3-pro.md", "id": 39, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3", "o3-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 61.4, "coding": 54.5, "reasoning": 70.9, "multimodalGrounded": 64.7, "knowledge": 66.6, "multilingual": 64.2, "instructionFollowing": 54.9, "math": 86.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 57, "categoryRanks": { "agentic": 29, "coding": 53, "reasoning": 23, "multimodalGrounded": 44, "knowledge": 41, "multilingual": 43, "instructionFollowing": 78, "math": 17 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 40.69, "aaGpqaDiamond": 84.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "o1", "canonicalModelKey": "o1", "model": "o1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 57, "rankingEligible": true, "overallRank": 58, "url": "https://benchlm.ai/models/o1", "markdownUrl": "https://benchlm.ai/md/models/o1.md", "id": 58, "releaseDate": "2024-12-01", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1-pro", "o1-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "o1-preview" }, "scores": { "displayScore": 57, "overallScore": 65, "rawOverallScore": 65, "verifiedDisplayScore": 81, "displayCategoryScores": { "agentic": 56.4, "coding": 48.2, "reasoning": 75, "multimodalGrounded": 58.9, "knowledge": 61.1, "multilingual": 56, "instructionFollowing": 92.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.7, "multilingual": null, "instructionFollowing": 92.2, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 58, "categoryRanks": { "agentic": 35, "reasoning": 20, "multimodalGrounded": 54, "multilingual": 59, "instructionFollowing": 13 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 31.08, "tau2Bench": 62.6, "gdpvalAaNormalized": 11.5, "gdpvalAa": 730 }, "coding": { "aaCodingIndex": 20.51, "terminalBenchHard": 12.9, "aaSciCode": 35.8 }, "reasoning": { "lcr": 59.3, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "mmlu": 91.8, "gpqa": 75.7, "artificialAnalysis": 30.75, "aaGpqaDiamond": 74.7, "aaHle": 7.7, "aaOmniscienceIndex": -10.5, "omniscienceAccuracy": 34.7, "omniscienceHallucinationRate": 69.3 }, "multilingual": {}, "instructionFollowing": { "ifeval": 92.2, "aaIfBench": 70.3 }, "math": {}, "korean": {} } }, { "slug": "deepseek-v3-2", "canonicalModelKey": "deepseek-v3-2", "model": "DeepSeek V3.2", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 56, "rankingEligible": true, "overallRank": 59, "url": "https://benchlm.ai/models/deepseek-v3-2", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2.md", "id": 84, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-2", "familyName": "DeepSeek V3.2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-2", "relatedModelKeys": [ "deepseek-v3-2-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 56, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 50, "coding": 57.3, "reasoning": 47.4, "multimodalGrounded": 50, "knowledge": 59.9, "multilingual": 67, "instructionFollowing": 61.7, "math": 70.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 60.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 59, "categoryRanks": { "agentic": 46, "coding": 51, "reasoning": 56, "multimodalGrounded": 69, "knowledge": 51, "multilingual": 39, "instructionFollowing": 68, "math": 34 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 42, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 40.2, "vitaBench": 18.5, "aaAgenticIndex": 39.82, "tau2Bench": 78.9, "gdpvalAaNormalized": 18.8, "gdpvalAa": 876, "gertLabs": 29.57 }, "coding": { "sweRebench": 60.9, "reactNativeEvals": 71.5, "aaCodingIndex": 34.6, "terminalBenchHard": 32.6, "aaSciCode": 38.7 }, "reasoning": { "lcr": 39, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1222 }, "knowledge": { "artificialAnalysis": 32.09, "aaGpqaDiamond": 75.1, "aaHle": 10.5, "aaOmniscienceIndex": -46.7, "omniscienceAccuracy": 24.2, "omniscienceHallucinationRate": 93.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 49 }, "math": {} } }, { "slug": "claude-haiku-4-5", "canonicalModelKey": "claude-haiku-4-5", "model": "Claude Haiku 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 56, "rankingEligible": true, "overallRank": 60, "url": "https://benchlm.ai/models/claude-haiku-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5.md", "id": 78, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "claude-haiku-4-5", "familyName": "Claude Haiku 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-haiku-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 56, "overallScore": 54, "rawOverallScore": 54, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 44.2, "coding": 53.2, "reasoning": 58.6, "multimodalGrounded": 73.6, "knowledge": 48.3, "multilingual": 61.4, "instructionFollowing": 69.6, "math": 55 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 73.3, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 60, "categoryRanks": { "agentic": 53, "coding": 56, "reasoning": 39, "multimodalGrounded": 24, "knowledge": 64, "multilingual": 52, "instructionFollowing": 53, "math": 44 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "sweVerified": 73.3 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1167 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "o3", "canonicalModelKey": "o3", "model": "o3", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 56, "rankingEligible": true, "overallRank": 61, "url": "https://benchlm.ai/models/o3", "markdownUrl": "https://benchlm.ai/md/models/o3.md", "id": 50, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3-pro", "o3-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 56, "overallScore": 68, "rawOverallScore": 68, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 56.5, "coding": 65.1, "reasoning": 55.2, "multimodalGrounded": 61.7, "knowledge": 65.4, "multilingual": 64.2, "instructionFollowing": 65.9, "math": 83.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 61, "categoryRanks": { "agentic": 34, "coding": 45, "reasoning": 46, "multimodalGrounded": 50, "knowledge": 44, "multilingual": 44, "instructionFollowing": 58, "math": 19 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 36, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 36.09, "tau2Bench": 80.7, "gdpvalAaNormalized": 12.8, "gdpvalAa": 757 }, "coding": { "aaCodingIndex": 38.4, "terminalBenchHard": 37.1, "aaSciCode": 41 }, "reasoning": { "lcr": 69.3, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 70.1, "designArenaWebsite": 1082 }, "knowledge": { "artificialAnalysis": 38.37, "aaGpqaDiamond": 82.7, "aaHle": 20, "aaOmniscienceIndex": -15.3, "omniscienceAccuracy": 38.4, "omniscienceHallucinationRate": 87.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.4 }, "math": {} } }, { "slug": "qwen3-5-35b-a3b", "canonicalModelKey": "qwen3-5-35b-a3b", "model": "Qwen3.5-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 55, "rankingEligible": true, "overallRank": 62, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "id": 60, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-35b-a3b", "familyName": "Qwen3.5-35B-A3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-35b-a3b", "relatedModelKeys": [ "qwen3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 58, "rawOverallScore": 58, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": 44.7, "coding": 59.1, "reasoning": 35.2, "multimodalGrounded": 63.3, "knowledge": 75.3, "multilingual": 67.2, "instructionFollowing": 81.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 50.6, "coding": 58.4, "reasoning": 59, "multimodalGrounded": null, "knowledge": 79.3, "multilingual": 81, "instructionFollowing": 91.9, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 62, "categoryRanks": { "agentic": 51, "coding": 50, "multimodalGrounded": 47, "knowledge": 28, "multilingual": 38, "instructionFollowing": 34 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 19, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 40.5, "browseComp": 61, "osWorldVerified": 54.5, "tau2Bench": 89.2, "aaAgenticIndex": 44.11, "gdpvalAaNormalized": 20.3, "gdpvalAa": 905, "gertLabs": 28.96 }, "coding": { "sweVerified": 69.2, "sweRebench": 53.7, "aaCodingIndex": 30.25, "terminalBenchHard": 26.5, "aaSciCode": 37.7 }, "reasoning": { "longBenchV2": 59, "lcr": 62.7, "critpt": 0.9 }, "multimodalGrounded": { "mmmu": 81.4, "mmvu": 72.3, "mathVision": 83.9, "vStar": 92.7, "aaMmmuPro": 72.7 }, "knowledge": { "mmluPro": 85.3, "superGpqa": 63.4, "gpqa": 84.2, "artificialAnalysis": 37.12, "aaGpqaDiamond": 84.5, "aaHle": 19.7, "aaOmniscienceIndex": -46.4, "omniscienceAccuracy": 20.5, "omniscienceHallucinationRate": 84 }, "multilingual": { "mmluProX": 81 }, "instructionFollowing": { "ifeval": 91.9, "aaIfBench": 72.5 }, "math": {} } }, { "slug": "gemini-3-flash", "canonicalModelKey": "gemini-3-flash", "model": "Gemini 3 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 55, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-flash.md", "id": 77, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-flash", "familyName": "Gemini 3 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 44.7, "coding": 47.5, "reasoning": 66.1, "multimodalGrounded": 72, "knowledge": 46.3, "multilingual": 62.5, "instructionFollowing": 66.9, "math": 52.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 63, "categoryRanks": { "agentic": 52, "coding": 62, "reasoning": 30, "multimodalGrounded": 27, "knowledge": 66, "multilingual": 48, "instructionFollowing": 57, "math": 48 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 41, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 49.2, "aaAgenticIndex": 35.01, "tau2Bench": 43.3, "gdpvalAaNormalized": 30.7, "gdpvalAa": 1114, "gertLabs": 56.63 }, "coding": { "vibeCodeBench": 20.204, "aaCodingIndex": 37.84, "terminalBenchHard": 31.8, "aaSciCode": 49.9 }, "reasoning": { "lcr": 48, "critpt": 1.4 }, "multimodalGrounded": { "aaMmmuPro": 78.6, "designArenaWebsite": 1241 }, "knowledge": { "artificialAnalysis": 35.05, "aaGpqaDiamond": 81.2, "aaHle": 14.1, "aaOmniscienceIndex": -3.6, "omniscienceAccuracy": 45.5, "omniscienceHallucinationRate": 90.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 55.1 }, "math": {} } }, { "slug": "o3-mini", "canonicalModelKey": "o3-mini", "model": "o3-mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 55, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/o3-mini", "markdownUrl": "https://benchlm.ai/md/models/o3-mini.md", "id": 41, "releaseDate": "2025-01-31", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3", "o3-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": 64, "displayCategoryScores": { "agentic": 61.7, "coding": 49.4, "reasoning": 68, "multimodalGrounded": 65.6, "knowledge": 60.9, "multilingual": 44.8, "instructionFollowing": 85.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 49.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 77.2, "multilingual": null, "instructionFollowing": 93.9, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 64, "categoryRanks": { "agentic": 26, "reasoning": 27, "multimodalGrounded": 38, "multilingual": 64, "instructionFollowing": 24 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 28.7 }, "coding": { "sweVerified": 49.3, "aaCodingIndex": 17.86, "terminalBenchHard": 6.8, "aaSciCode": 39.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmlu": 86.9, "gpqa": 77.2, "artificialAnalysis": 25.86, "aaGpqaDiamond": 74.8, "aaHle": 8.7 }, "multilingual": {}, "instructionFollowing": { "ifeval": 93.9 }, "math": { "aime2024": 87.3 } } }, { "slug": "minimax-m2-7", "canonicalModelKey": "minimax-m2-7", "model": "MiniMax M2.7", "creator": "MiniMax", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 53, "rankingEligible": true, "overallRank": 65, "url": "https://benchlm.ai/models/minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-7.md", "id": 117, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m2-7", "familyName": "MiniMax M2.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m2-7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": "minimax-m2-5" }, "scores": { "displayScore": 53, "overallScore": 53, "rawOverallScore": 53, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 48.6, "coding": 54, "reasoning": null, "multimodalGrounded": null, "knowledge": 50.3, "multilingual": null, "instructionFollowing": 76.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 57, "coding": 53.7, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 65, "categoryRanks": { "coding": 54, "instructionFollowing": 46 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 31, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 57, "tau2Bench": 84.8, "toolathlon": 46.3, "mleBenchLite": 66.6, "mmClawBench": 62.7, "clawEval": 48.7, "aaAgenticIndex": 61.49, "apexAgentsAa": 10.6, "gdpvalAaNormalized": 50.2, "gdpvalAa": 1505, "gertLabs": 40.4 }, "coding": { "sweVerifiedArcee": 75.4, "swePro": 56.2, "sweRebench": 51.9, "sweMultilingual": 76.5, "multiSweBench": 52.7, "vibePro": 55.6, "nl2Repo": 39.8, "vibeCodeBench": 27.037, "reactNativeEvals": 71.4, "aaCodingIndex": 41.93, "terminalBenchHard": 39.4, "aaSciCode": 47 }, "reasoning": { "lcr": 68.7, "critpt": 0.6 }, "multimodalGrounded": { "gdpvalAa": 1495, "designArenaWebsite": 1287 }, "knowledge": { "gpqaDiamond": 87, "mmluProArcee": 80.8, "artificialAnalysis": 49.62, "aaGpqaDiamond": 87.4, "aaHle": 28.1, "aaOmniscienceIndex": 0.7, "omniscienceAccuracy": 26.1, "omniscienceHallucinationRate": 34.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.7 }, "math": { "aime2025Arcee": 80 } } }, { "slug": "deepseek-coder-2-0", "canonicalModelKey": "deepseek-coder-2-0", "model": "DeepSeek Coder 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 51, "rankingEligible": true, "overallRank": 66, "url": "https://benchlm.ai/models/deepseek-coder-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-coder-2-0.md", "id": 61, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseek-coder-2-0", "familyName": "DeepSeek Coder 2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-coder-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 51, "overallScore": 62, "rawOverallScore": 62, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 59.8, "coding": 60.9, "reasoning": 59.5, "multimodalGrounded": 36.2, "knowledge": 55.6, "multilingual": 60.6, "instructionFollowing": 69.6, "math": 70.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 66, "categoryRanks": { "agentic": 30, "coding": 48, "reasoning": 36, "multimodalGrounded": 80, "knowledge": 57, "multilingual": 53, "instructionFollowing": 54, "math": 32 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-4-1-opus", "canonicalModelKey": "claude-4-1-opus", "model": "Claude 4.1 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 51, "rankingEligible": true, "overallRank": 67, "url": "https://benchlm.ai/models/claude-4-1-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus.md", "id": 69, "releaseDate": "2025-08-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-1-opus", "familyName": "Claude 4.1 Opus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-1-opus", "relatedModelKeys": [ "claude-4-1-opus-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 51, "overallScore": 59, "rawOverallScore": 59, "verifiedDisplayScore": 75, "displayCategoryScores": { "agentic": 38.8, "coding": 56.4, "reasoning": 55.7, "multimodalGrounded": 77.3, "knowledge": 51.8, "multilingual": 66.2, "instructionFollowing": 58.6, "math": 64.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 74.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 67, "categoryRanks": { "agentic": 62, "coding": 52, "reasoning": 43, "multimodalGrounded": 20, "knowledge": 59, "multilingual": 41, "instructionFollowing": 72, "math": 39 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "sweVerified": 74.5 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1222 }, "knowledge": { "artificialAnalysis": 36 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-llm-2-0", "canonicalModelKey": "deepseek-llm-2-0", "model": "DeepSeek LLM 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 50, "rankingEligible": true, "overallRank": 68, "url": "https://benchlm.ai/models/deepseek-llm-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-llm-2-0.md", "id": 79, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseek-llm-2-0", "familyName": "DeepSeek LLM 2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-llm-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 54, "rawOverallScore": 54, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 49.4, "coding": 45.6, "reasoning": 58.4, "multimodalGrounded": 47.5, "knowledge": 53.4, "multilingual": 57.8, "instructionFollowing": 65.9, "math": 70.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 68, "categoryRanks": { "agentic": 47, "coding": 64, "reasoning": 41, "multimodalGrounded": 72, "knowledge": 58, "multilingual": 57, "instructionFollowing": 59, "math": 33 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen2-5-1m", "canonicalModelKey": "qwen2-5-1m", "model": "Qwen2.5-1M", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50, "rankingEligible": true, "overallRank": 69, "url": "https://benchlm.ai/models/qwen2-5-1m", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-1m.md", "id": 54, "releaseDate": "2025-01-27", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-1m", "familyName": "Qwen2.5-1M", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-1m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 54.6, "coding": 48.6, "reasoning": 70.6, "multimodalGrounded": 54.3, "knowledge": 56.6, "multilingual": 62.3, "instructionFollowing": 62.3, "math": 76.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 69, "categoryRanks": { "agentic": 39, "coding": 60, "reasoning": 24, "multimodalGrounded": 64, "knowledge": 54, "multilingual": 50, "instructionFollowing": 65, "math": 26 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-4-sonnet", "canonicalModelKey": "claude-4-sonnet", "model": "Claude 4 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 50, "rankingEligible": true, "overallRank": 70, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md", "id": 67, "releaseDate": "2025-05-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-sonnet", "familyName": "Claude 4 Sonnet", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-sonnet", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 59, "rawOverallScore": 59, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 43.8, "coding": 53.4, "reasoning": 54.7, "multimodalGrounded": 75.5, "knowledge": 50.1, "multilingual": 67, "instructionFollowing": 58.6, "math": 61.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 72.7, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 70, "categoryRanks": { "agentic": 54, "coding": 55, "reasoning": 48, "multimodalGrounded": 23, "knowledge": 61, "multilingual": 40, "instructionFollowing": 73, "math": 41 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 39.21, "tau2Bench": 52.3, "gdpvalAaNormalized": 31.2, "gdpvalAa": 1123, "gertLabs": 39.66 }, "coding": { "sweVerified": 72.7, "aaCodingIndex": 30.6, "terminalBenchHard": 27.3, "aaSciCode": 37.3 }, "reasoning": { "lcr": 44.3, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 62.4, "designArenaWebsite": 1191 }, "knowledge": { "artificialAnalysis": 33, "aaGpqaDiamond": 68.3, "aaHle": 4, "aaOmniscienceIndex": -9.2, "omniscienceAccuracy": 22.4, "omniscienceHallucinationRate": 40.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 45.4 }, "math": {} } }, { "slug": "gpt-4o-mini", "canonicalModelKey": "gpt-4o-mini", "model": "GPT-4o mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md", "id": 101, "releaseDate": "2024-07-18", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o", "familyName": "GPT-4o", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o", "relatedModelKeys": [ "gpt-4o" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 39, "coding": 90.9, "reasoning": 20.6, "multimodalGrounded": 41.2, "knowledge": 49, "multilingual": 46.3, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 71, "categoryRanks": { "agentic": 59, "reasoning": 81, "multimodalGrounded": 75, "multilingual": 62 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 22.9 }, "reasoning": {}, "multimodalGrounded": { "aaMmmuPro": 41.5 }, "knowledge": { "artificialAnalysis": 12.65, "aaGpqaDiamond": 42.6, "aaHle": 4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31 }, "math": {}, "korean": {} } }, { "slug": "qwen2-5-72b", "canonicalModelKey": "qwen2-5-72b", "model": "Qwen2.5-72B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49, "rankingEligible": true, "overallRank": 72, "url": "https://benchlm.ai/models/qwen2-5-72b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-72b.md", "id": 73, "releaseDate": "2024-09-19", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-72b", "familyName": "Qwen2.5-72B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-72b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 46.4, "coding": 46.8, "reasoning": 60.1, "multimodalGrounded": 51.7, "knowledge": 56.4, "multilingual": 63.4, "instructionFollowing": 65.9, "math": 76.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 72, "categoryRanks": { "agentic": 49, "coding": 63, "reasoning": 35, "multimodalGrounded": 67, "knowledge": 55, "multilingual": 47, "instructionFollowing": 60, "math": 27 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseekmath-v2", "canonicalModelKey": "deepseekmath-v2", "model": "DeepSeekMath V2", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49, "rankingEligible": true, "overallRank": 73, "url": "https://benchlm.ai/models/deepseekmath-v2", "markdownUrl": "https://benchlm.ai/md/models/deepseekmath-v2.md", "id": 62, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseekmath", "familyName": "DeepSeekMath", "variantType": "snapshot", "snapshotLabel": "V2", "baseFamilyModelKey": "deepseekmath-v2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 61, "rawOverallScore": 61, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 53.4, "coding": 51.3, "reasoning": 60.2, "multimodalGrounded": 53.9, "knowledge": 57.3, "multilingual": 68.1, "instructionFollowing": 58.6, "math": 74.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 73, "categoryRanks": { "agentic": 43, "coding": 58, "reasoning": 34, "multimodalGrounded": 66, "knowledge": 53, "multilingual": 36, "instructionFollowing": 74, "math": 29 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mistral-large-3", "canonicalModelKey": "mistral-large-3", "model": "Mistral Large 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 48, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/mistral-large-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-3.md", "id": 99, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "mistral-large-3", "familyName": "Mistral Large 3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-large-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 37.4, "coding": 37.5, "reasoning": 52, "multimodalGrounded": 67.7, "knowledge": 41.1, "multilingual": 57.8, "instructionFollowing": 67, "math": 64.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 74, "categoryRanks": { "agentic": 65, "coding": 69, "reasoning": 51, "multimodalGrounded": 33, "knowledge": 73, "multilingual": 58, "instructionFollowing": 56, "math": 40 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 36, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 21.7, "tau2Bench": 24.6, "gdpvalAaNormalized": 18.2, "gdpvalAa": 864 }, "coding": { "aaCodingIndex": 22.68, "terminalBenchHard": 15.9, "aaSciCode": 36.2 }, "reasoning": { "lcr": 34.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 55.7 }, "knowledge": { "artificialAnalysis": 22.8, "aaGpqaDiamond": 68, "aaHle": 4.1, "aaOmniscienceIndex": -39.4, "omniscienceAccuracy": 24.1, "omniscienceHallucinationRate": 83.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.2 }, "math": {} } }, { "slug": "gemini-3-1-flash-lite", "canonicalModelKey": "gemini-3-1-flash-lite", "model": "Gemini 3.1 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 47, "rankingEligible": true, "overallRank": 75, "url": "https://benchlm.ai/models/gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-lite.md", "id": 113, "releaseDate": "2026-03-03", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-1-flash-lite", "familyName": "Gemini 3.1 Flash-Lite", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-1-flash-lite", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 47, "overallScore": 38, "rawOverallScore": 38, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 41.2, "coding": 25.8, "reasoning": 58.8, "multimodalGrounded": 58.3, "knowledge": 35.5, "multilingual": 32.7, "instructionFollowing": 44, "math": 43.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 73.2, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 75, "categoryRanks": { "agentic": 57, "coding": 75, "reasoning": 38, "multimodalGrounded": 57, "knowledge": 78, "multilingual": 77, "instructionFollowing": 90, "math": 57 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 25.67, "apexAgentsAa": 12.2, "tau2Bench": 31.3, "gdpvalAaNormalized": 21.3, "gdpvalAa": 926, "gertLabs": 38.46 }, "coding": { "vibeCodeBench": 0, "aaCodingIndex": 30.13, "terminalBenchHard": 24.2, "aaSciCode": 41.9 }, "reasoning": { "lcr": 65.3, "critpt": 1.1 }, "multimodalGrounded": { "charxiv": 73.2, "aaMmmuPro": 75.5 }, "knowledge": { "artificialAnalysis": 33.52, "aaGpqaDiamond": 82.2, "aaHle": 16.2, "aaOmniscienceIndex": -15.5, "omniscienceAccuracy": 36.4, "omniscienceHallucinationRate": 81.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 77.2 }, "math": {} } }, { "slug": "qwen3-235b-2507-reasoning", "canonicalModelKey": "qwen3-235b-2507-reasoning", "model": "Qwen3 235B 2507 (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 45, "rankingEligible": true, "overallRank": 76, "url": "https://benchlm.ai/models/qwen3-235b-2507-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507-reasoning.md", "id": 119, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-235b-2507", "familyName": "Qwen3 235B 2507", "variantType": "reasoning", "snapshotLabel": "2507", "baseFamilyModelKey": "qwen3-235b-2507", "relatedModelKeys": [ "qwen3-235b-2507" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 45, "overallScore": 34, "rawOverallScore": 34, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 38.9, "coding": 41.5, "reasoning": 35.9, "multimodalGrounded": 7.3, "knowledge": 43.5, "multilingual": 45.6, "instructionFollowing": 76.2, "math": 40.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 76, "categoryRanks": { "agentic": 60, "coding": 67, "reasoning": 66, "multimodalGrounded": 98, "knowledge": 71, "multilingual": 63, "instructionFollowing": 47, "math": 60 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-4-1-mini", "canonicalModelKey": "gpt-4-1-mini", "model": "GPT-4.1 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 45, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md", "id": 91, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1", "gpt-4-1-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-4o-mini" }, "scores": { "displayScore": 45, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": 43.3, "coding": 24.3, "reasoning": 80.3, "multimodalGrounded": 56.8, "knowledge": 49.4, "multilingual": 42, "instructionFollowing": 78.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 23.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 64.2, "multilingual": null, "instructionFollowing": 88.5, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 77, "categoryRanks": { "agentic": 56, "reasoning": 16, "multimodalGrounded": 60, "multilingual": 67, "instructionFollowing": 41 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 25.15, "tau2Bench": 52.9, "gdpvalAaNormalized": 6, "gdpvalAa": 619 }, "coding": { "sweVerified": 23.6, "aaCodingIndex": 18.52, "terminalBenchHard": 7.6, "aaSciCode": 40.4 }, "reasoning": { "lcr": 42.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 58.7, "designArenaWebsite": 1043 }, "knowledge": { "mmlu": 87.5, "gpqa": 64.2, "artificialAnalysis": 22.9, "aaGpqaDiamond": 66.4, "aaHle": 4.6, "aaOmniscienceIndex": -50.1, "omniscienceAccuracy": 17.5, "omniscienceHallucinationRate": 82 }, "multilingual": {}, "instructionFollowing": { "ifeval": 88.5, "aaIfBench": 38.3 }, "math": {}, "korean": {} } }, { "slug": "nemotron-3-super-100b", "canonicalModelKey": "nemotron-3-super-100b", "model": "Nemotron 3 Super 100B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 43, "rankingEligible": true, "overallRank": 78, "url": "https://benchlm.ai/models/nemotron-3-super-100b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-100b.md", "id": 92, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-super-100b", "familyName": "Nemotron 3 Super 100B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-super-100b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 43.6, "coding": 43, "reasoning": 57, "multimodalGrounded": 40, "knowledge": 44, "multilingual": 59.7, "instructionFollowing": 62.3, "math": 52.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 78, "categoryRanks": { "agentic": 55, "coding": 66, "reasoning": 42, "multimodalGrounded": 77, "knowledge": 70, "multilingual": 54, "instructionFollowing": 66, "math": 47 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 5.5 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "o4-mini-high", "canonicalModelKey": "o4-mini-high", "model": "o4-mini (high)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 43, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/o4-mini-high", "markdownUrl": "https://benchlm.ai/md/models/o4-mini-high.md", "id": 90, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o4-mini", "familyName": "o4-mini", "variantType": "reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "o4-mini-high", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 38.7, "coding": 45.5, "reasoning": 48.1, "multimodalGrounded": 50.3, "knowledge": 58, "multilingual": 66.1, "instructionFollowing": 58.6, "math": 54.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 79, "categoryRanks": { "agentic": 63, "coding": 65, "reasoning": 55, "multimodalGrounded": 68, "knowledge": 52, "multilingual": 42, "instructionFollowing": 75, "math": 45 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 39, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-4-1-opus-thinking", "canonicalModelKey": "claude-4-1-opus-thinking", "model": "Claude 4.1 Opus Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 43, "rankingEligible": true, "overallRank": 80, "url": "https://benchlm.ai/models/claude-4-1-opus-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus-thinking.md", "id": 98, "releaseDate": "2025-08-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-1-opus", "familyName": "Claude 4.1 Opus", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-1-opus", "relatedModelKeys": [ "claude-4-1-opus" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 48, "rawOverallScore": 48, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 24.9, "coding": 51.3, "reasoning": 49.2, "multimodalGrounded": 65.7, "knowledge": 35.2, "multilingual": 50.5, "instructionFollowing": 76.9, "math": 52.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 80, "categoryRanks": { "agentic": 75, "coding": 59, "reasoning": 54, "multimodalGrounded": 37, "knowledge": 80, "multilingual": 60, "instructionFollowing": 45, "math": 46 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 71.4 }, "coding": { "aaCodingIndex": 36.52, "terminalBenchHard": 34.3, "aaSciCode": 40.9 }, "reasoning": { "lcr": 66.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 67.9 }, "knowledge": { "artificialAnalysis": 42, "aaGpqaDiamond": 80.9, "aaHle": 11.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 55.4 }, "math": {} } }, { "slug": "gpt-4o", "canonicalModelKey": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md", "id": 108, "releaseDate": "2024-05-13", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o", "familyName": "GPT-4o", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o", "relatedModelKeys": [ "gpt-4o-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 38.9, "coding": 24.4, "reasoning": 46.8, "multimodalGrounded": 62.2, "knowledge": 35.6, "multilingual": 48.7, "instructionFollowing": 54.9, "math": 52 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 81, "categoryRanks": { "agentic": 61, "coding": 76, "reasoning": 57, "multimodalGrounded": 49, "knowledge": 77, "multilingual": 61, "instructionFollowing": 79, "math": 49 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 8.38, "tau2Bench": 25.1, "gdpvalAaNormalized": 0, "gdpvalAa": 348 }, "coding": { "aaCodingIndex": 16.67, "terminalBenchHard": 8.3, "aaSciCode": 33.3 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 876 }, "knowledge": { "artificialAnalysis": 17.32, "aaGpqaDiamond": 54.3, "aaHle": 3.3, "aaOmniscienceIndex": -10.7, "omniscienceAccuracy": 19.7, "omniscienceHallucinationRate": 37.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 34.3 }, "math": {}, "korean": {} } }, { "slug": "kimi-k2", "canonicalModelKey": "kimi-k2", "model": "Kimi K2", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 41, "rankingEligible": true, "overallRank": 82, "url": "https://benchlm.ai/models/kimi-k2", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2.md", "id": 96, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2", "familyName": "Kimi K2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 30.2, "coding": 53.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 56, "multilingual": null, "instructionFollowing": 83.5, "math": 51.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 82, "categoryRanks": { "knowledge": 56, "instructionFollowing": 30, "math": 51 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 18, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 61.1, "aaAgenticIndex": 24.27, "gdpvalAaNormalized": 1.2, "gdpvalAa": 525 }, "coding": { "aaCodingIndex": 22.1, "terminalBenchHard": 15.9, "aaSciCode": 34.5 }, "reasoning": { "lcr": 51, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1096 }, "knowledge": { "artificialAnalysis": 26.32, "aaGpqaDiamond": 76.6, "aaHle": 7, "aaOmniscienceIndex": -27.5, "omniscienceAccuracy": 26.8, "omniscienceHallucinationRate": 74.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.5 }, "math": {} } }, { "slug": "llama-3-1-405b", "canonicalModelKey": "llama-3-1-405b", "model": "Llama 3.1 405B", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40, "rankingEligible": true, "overallRank": 83, "url": "https://benchlm.ai/models/llama-3-1-405b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-1-405b.md", "id": 97, "releaseDate": "2024-07-23", "market": null, "isRegional": false, "family": { "familyKey": "llama-3-1-405b", "familyName": "Llama 3.1 405B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-3-1-405b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 40, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 31.4, "coding": 36.5, "reasoning": 50.3, "multimodalGrounded": 43.8, "knowledge": 45.2, "multilingual": 61.6, "instructionFollowing": 69.6, "math": 58 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 83, "categoryRanks": { "agentic": 72, "coding": 70, "reasoning": 52, "multimodalGrounded": 74, "knowledge": 67, "multilingual": 51, "instructionFollowing": 55, "math": 42 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 6.34, "tau2Bench": 19, "gdpvalAaNormalized": 0, "gdpvalAa": 255 }, "coding": { "aaCodingIndex": 14.5, "terminalBenchHard": 6.8, "aaSciCode": 29.9 }, "reasoning": { "lcr": 24.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 17.38, "aaGpqaDiamond": 51.5, "aaHle": 4.2, "aaOmniscienceIndex": -17.3, "omniscienceAccuracy": 22.3, "omniscienceHallucinationRate": 51 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39 }, "math": {} } }, { "slug": "claude-3-5-sonnet", "canonicalModelKey": "claude-3-5-sonnet", "model": "Claude 3.5 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 40, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/claude-3-5-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-3-5-sonnet.md", "id": 95, "releaseDate": "2024-06-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-5-sonnet", "familyName": "Claude 3.5 Sonnet", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-5-sonnet", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 40, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 38.4, "coding": 40.3, "reasoning": 49.8, "multimodalGrounded": 66.9, "knowledge": 39.1, "multilingual": 62.5, "instructionFollowing": 58.6, "math": 50.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 84, "categoryRanks": { "agentic": 64, "coding": 68, "reasoning": 53, "multimodalGrounded": 35, "knowledge": 75, "multilingual": 49, "instructionFollowing": 76, "math": 52 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "sweVerified": 49 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 59.4 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-code-fast-1", "canonicalModelKey": "grok-code-fast-1", "model": "Grok Code Fast 1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 39, "rankingEligible": true, "overallRank": 85, "url": "https://benchlm.ai/models/grok-code-fast-1", "markdownUrl": "https://benchlm.ai/md/models/grok-code-fast-1.md", "id": 93, "releaseDate": "2025-08-28", "market": null, "isRegional": false, "family": { "familyKey": "grok-code-fast-1", "familyName": "Grok Code Fast 1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-code-fast-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 39, "overallScore": 48, "rawOverallScore": 48, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 40.1, "coding": 61.6, "reasoning": 43.1, "multimodalGrounded": 21.2, "knowledge": 34.7, "multilingual": 43.7, "instructionFollowing": 44, "math": 45.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 85, "categoryRanks": { "agentic": 58, "coding": 47, "reasoning": 60, "multimodalGrounded": 88, "knowledge": 82, "multilingual": 65, "instructionFollowing": 91, "math": 55 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 35.63, "tau2Bench": 75.7, "gdpvalAaNormalized": 13.1, "gdpvalAa": 763 }, "coding": { "sweVerified": 70.8, "aaCodingIndex": 23.69, "terminalBenchHard": 17.4, "aaSciCode": 36.2 }, "reasoning": { "lcr": 48.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 28.74, "aaGpqaDiamond": 72.7, "aaHle": 7.5, "aaOmniscienceIndex": -36, "omniscienceAccuracy": 23.8, "omniscienceHallucinationRate": 78.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.4 }, "math": {} } }, { "slug": "sarvam-105b", "canonicalModelKey": "sarvam-105b", "model": "Sarvam 105B", "creator": "Sarvam", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 39, "rankingEligible": true, "overallRank": 86, "url": "https://benchlm.ai/models/sarvam-105b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-105b.md", "id": 115, "releaseDate": "2026-03-06", "market": null, "isRegional": false, "family": { "familyKey": "sarvam-105b", "familyName": "Sarvam 105B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "sarvam-105b", "relatedModelKeys": [ "sarvam-30b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "sarvam-m" }, "scores": { "displayScore": 39, "overallScore": 45, "rawOverallScore": 45, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 28.9, "coding": 36.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 49.2, "multilingual": null, "instructionFollowing": 65.2, "math": 90.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 86, "categoryRanks": { "instructionFollowing": 61, "math": 14 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 24.69, "tau2Bench": 46.8, "gdpvalAaNormalized": 11.9, "gdpvalAa": 738 }, "coding": { "aaCodingIndex": 9.81, "terminalBenchHard": 1.5, "aaSciCode": 26.4 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 18.16, "aaGpqaDiamond": 73.8, "aaHle": 10.1, "aaOmniscienceIndex": -59.5, "omniscienceAccuracy": 17.6, "omniscienceHallucinationRate": 93.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 34.4 }, "math": {} } }, { "slug": "mistral-large-2", "canonicalModelKey": "mistral-large-2", "model": "Mistral Large 2", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 38, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/mistral-large-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-2.md", "id": 100, "releaseDate": "2024-07-24", "market": null, "isRegional": false, "family": { "familyKey": "mistral-large-2", "familyName": "Mistral Large 2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-large-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 38, "overallScore": 48, "rawOverallScore": 48, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 32.5, "coding": 32.6, "reasoning": 44.8, "multimodalGrounded": 41.1, "knowledge": 47.7, "multilingual": 58.7, "instructionFollowing": 50.6, "math": 47.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 87, "categoryRanks": { "agentic": 71, "coding": 71, "reasoning": 58, "multimodalGrounded": 76, "knowledge": 65, "multilingual": 56, "instructionFollowing": 83, "math": 53 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 10.23, "tau2Bench": 30.7, "gdpvalAaNormalized": 0, "gdpvalAa": 323 }, "coding": { "aaCodingIndex": 13.76, "terminalBenchHard": 6.1, "aaSciCode": 29.2 }, "reasoning": { "lcr": 5.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 15.09, "aaGpqaDiamond": 48.6, "aaHle": 4, "aaOmniscienceIndex": -34, "omniscienceAccuracy": 20.1, "omniscienceHallucinationRate": 67.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31.2 }, "math": {} } }, { "slug": "gemini-2-5-flash", "canonicalModelKey": "gemini-2-5-flash", "model": "Gemini 2.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 37, "rankingEligible": true, "overallRank": 88, "url": "https://benchlm.ai/models/gemini-2-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash.md", "id": 125, "releaseDate": "2025-06-17", "market": null, "isRegional": false, "family": { "familyKey": "gemini-2-5-flash", "familyName": "Gemini 2.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-2-5-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 37, "overallScore": 32, "rawOverallScore": 32, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 33, "coding": 16.5, "reasoning": 44, "multimodalGrounded": 54, "knowledge": 26.6, "multilingual": 35.5, "instructionFollowing": 41.8, "math": 27.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 88, "categoryRanks": { "agentic": 69, "coding": 85, "reasoning": 59, "multimodalGrounded": 65, "knowledge": 88, "multilingual": 73, "instructionFollowing": 94, "math": 72 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 15.01, "tau2Bench": 14.9, "gdpvalAaNormalized": 11.9, "gdpvalAa": 739 }, "coding": { "aaCodingIndex": 17.76, "terminalBenchHard": 12.1, "aaSciCode": 29.1 }, "reasoning": { "lcr": 45.9, "critpt": 1.4 }, "multimodalGrounded": { "aaMmmuPro": 65.5, "designArenaWebsite": 1160 }, "knowledge": { "artificialAnalysis": 20.56, "aaGpqaDiamond": 68.3, "aaHle": 5.1, "aaOmniscienceIndex": -42, "omniscienceAccuracy": 26.5, "omniscienceHallucinationRate": 93.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39 }, "math": {} } }, { "slug": "gemini-1-5-pro", "canonicalModelKey": "gemini-1-5-pro", "model": "Gemini 1.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 35, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/gemini-1-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-5-pro.md", "id": 114, "releaseDate": "2024-02-15", "market": null, "isRegional": false, "family": { "familyKey": "gemini-1-5-pro", "familyName": "Gemini 1.5 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-1-5-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 35, "overallScore": 38, "rawOverallScore": 38, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 33.7, "coding": 14.9, "reasoning": 52.8, "multimodalGrounded": 65.5, "knowledge": 35.5, "multilingual": 31.9, "instructionFollowing": 36.6, "math": 45.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 89, "categoryRanks": { "agentic": 67, "coding": 87, "reasoning": 50, "multimodalGrounded": 39, "knowledge": 79, "multilingual": 80, "instructionFollowing": 100, "math": 56 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 23.63, "aaSciCode": 29.5 }, "reasoning": {}, "multimodalGrounded": { "aaMmmuPro": 55 }, "knowledge": { "artificialAnalysis": 15.99, "aaGpqaDiamond": 58.9, "aaHle": 4.9 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-v3", "canonicalModelKey": "deepseek-v3", "model": "DeepSeek V3", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34, "rankingEligible": true, "overallRank": 90, "url": "https://benchlm.ai/models/deepseek-v3", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3.md", "id": 112, "releaseDate": "2024-12-26", "market": null, "isRegional": false, "family": { "familyKey": "deepseek", "familyName": "DeepSeek", "variantType": "snapshot", "snapshotLabel": "V3", "baseFamilyModelKey": "deepseek-v3", "relatedModelKeys": [ "deepseek-v3-1", "deepseek-v3-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 34, "overallScore": 39, "rawOverallScore": 39, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 28.5, "reasoning": 16.5, "multimodalGrounded": null, "knowledge": 42.7, "multilingual": null, "instructionFollowing": 61.2, "math": 69.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 90, "categoryRanks": { "knowledge": 72, "instructionFollowing": 69 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 8.83, "tau2Bench": 22.8, "gdpvalAaNormalized": 0, "gdpvalAa": 409 }, "coding": { "liveCodeBench": 37.6, "sweVerified": 42, "aaCodingIndex": 16.35, "terminalBenchHard": 6.8, "aaSciCode": 35.4 }, "reasoning": { "lcr": 29, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1165 }, "knowledge": { "gpqa": 59.1, "mmluPro": 75.9, "artificialAnalysis": 16.46, "aaGpqaDiamond": 55.7, "aaHle": 3.6, "aaOmniscienceIndex": -41.3, "omniscienceAccuracy": 25.4, "omniscienceHallucinationRate": 89.4 }, "multilingual": {}, "instructionFollowing": { "ifeval": 86.1, "aaIfBench": 34.8 }, "math": {} } }, { "slug": "gpt-oss-120b", "canonicalModelKey": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34, "rankingEligible": true, "overallRank": 91, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md", "id": 129, "releaseDate": "2025-08-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-oss", "familyName": "GPT-OSS", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-oss-120b", "relatedModelKeys": [ "gpt-oss-20b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 34, "overallScore": 28, "rawOverallScore": 28, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 34.4, "coding": 21.4, "reasoning": 30.2, "multimodalGrounded": 18.9, "knowledge": 44.6, "multilingual": 35.3, "instructionFollowing": 38.5, "math": 26.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 91, "categoryRanks": { "agentic": 66, "coding": 78, "reasoning": 70, "multimodalGrounded": 91, "knowledge": 69, "multilingual": 74, "instructionFollowing": 98, "math": 73 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 37.87, "apexAgentsAa": 3.1, "tau2Bench": 65.8, "gdpvalAaNormalized": 22.4, "gdpvalAa": 947, "gertLabs": 29.61 }, "coding": { "reactNativeEvals": 71.6, "aaCodingIndex": 28.62, "terminalBenchHard": 23.5, "aaSciCode": 38.9 }, "reasoning": { "lcr": 50.7, "critpt": 1.1 }, "multimodalGrounded": { "designArenaWebsite": 1013 }, "knowledge": { "artificialAnalysis": 33.27, "aaGpqaDiamond": 78.2, "aaHle": 18.5, "aaOmniscienceIndex": -50, "omniscienceAccuracy": 21.5, "omniscienceHallucinationRate": 91.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 69 }, "math": {} } }, { "slug": "claude-3-opus", "canonicalModelKey": "claude-3-opus", "model": "Claude 3 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 34, "rankingEligible": true, "overallRank": 92, "url": "https://benchlm.ai/models/claude-3-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-3-opus.md", "id": 124, "releaseDate": "2024-03-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-opus", "familyName": "Claude 3 Opus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-opus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 34, "overallScore": 33, "rawOverallScore": 33, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 33.4, "coding": 13.4, "reasoning": 43, "multimodalGrounded": 58.9, "knowledge": 31.5, "multilingual": 32.7, "instructionFollowing": 36.6, "math": 42 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 92, "categoryRanks": { "agentic": 68, "coding": 88, "reasoning": 61, "multimodalGrounded": 55, "knowledge": 84, "multilingual": 78, "instructionFollowing": 101, "math": 59 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 19.53, "aaSciCode": 23.3 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 18, "aaGpqaDiamond": 48.9, "aaHle": 3.1 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "minicpm5-1b", "canonicalModelKey": "minicpm5-1b", "model": "MiniCPM5-1B", "creator": "OpenBMB", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 34, "rankingEligible": true, "overallRank": 93, "url": "https://benchlm.ai/models/minicpm5-1b", "markdownUrl": "https://benchlm.ai/md/models/minicpm5-1b.md", "id": 123, "releaseDate": "2026-05-25", "market": null, "isRegional": false, "family": { "familyKey": "minicpm5", "familyName": "MiniCPM5", "variantType": "1b", "snapshotLabel": null, "baseFamilyModelKey": "minicpm5-1b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 34, "overallScore": 34, "rawOverallScore": 34, "verifiedDisplayScore": 51, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 31.9, "math": 37 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 39.8, "multilingual": null, "instructionFollowing": 68.6, "math": 59.6 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 93, "categoryRanks": { "instructionFollowing": 110, "math": 64 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 25.15 }, "coding": { "liveCodeBenchPro": 22.68, "liveCodeBenchV6": 33.52 }, "reasoning": { "bbh": 71.89 }, "multimodalGrounded": {}, "knowledge": { "mmluPro": 48.85, "mmluRedux": 70.06, "gpqaDiamond": 26.26, "superGpqa": 23.14 }, "multilingual": {}, "instructionFollowing": { "ifBench": 46.67, "ifeval": 80.41 }, "math": { "aime2025": 40.42, "aime2026": 40.42, "hmmtFeb2026": 25.76, "math500": 91.6 } } }, { "slug": "deepseek-r1", "canonicalModelKey": "deepseek-r1", "model": "DeepSeek-R1", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 32, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/deepseek-r1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1.md", "id": 142, "releaseDate": "2025-01-20", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-r1", "familyName": "DeepSeek-R1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-r1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 32, "overallScore": 26, "rawOverallScore": 26, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 31.2, "coding": 26.4, "reasoning": 23.5, "multimodalGrounded": 17, "knowledge": 38.9, "multilingual": 6.4, "instructionFollowing": 54.6, "math": 33.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 94, "categoryRanks": { "agentic": 73, "coding": 74, "reasoning": 80, "multimodalGrounded": 94, "knowledge": 76, "multilingual": 91, "instructionFollowing": 80, "math": 67 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 20.84, "tau2Bench": 36.5, "gdpvalAaNormalized": 9, "gdpvalAa": 680 }, "coding": { "aaCodingIndex": 24.03, "terminalBenchHard": 15.9, "aaSciCode": 40.3 }, "reasoning": { "lcr": 54.7, "critpt": 1.4 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 27.07, "aaGpqaDiamond": 81.3, "aaHle": 14.9, "aaOmniscienceIndex": -27.1, "omniscienceAccuracy": 31, "omniscienceHallucinationRate": 84 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.6 }, "math": {} } }, { "slug": "qwen3-235b-2507", "canonicalModelKey": "qwen3-235b-2507", "model": "Qwen3 235B 2507", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 32, "rankingEligible": true, "overallRank": 95, "url": "https://benchlm.ai/models/qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507.md", "id": 144, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-235b-2507", "familyName": "Qwen3 235B 2507", "variantType": "base", "snapshotLabel": "2507", "baseFamilyModelKey": "qwen3-235b-2507", "relatedModelKeys": [ "qwen3-235b-2507-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 32, "overallScore": 23, "rawOverallScore": 23, "verifiedDisplayScore": 77, "displayCategoryScores": { "agentic": 16.4, "coding": 22.8, "reasoning": 25.6, "multimodalGrounded": 6.5, "knowledge": 40, "multilingual": 43.7, "instructionFollowing": 79.5, "math": 24.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 76.2, "multilingual": 79.4, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 95, "categoryRanks": { "agentic": 91, "coding": 77, "reasoning": 78, "multimodalGrounded": 100, "knowledge": 74, "multilingual": 66, "instructionFollowing": 40, "math": 74 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 77.5, "superGpqa": 62.6, "mmluPro": 83 }, "multilingual": { "mmluProX": 79.4 }, "instructionFollowing": {}, "math": {} } }, { "slug": "dbrx-instruct", "canonicalModelKey": "dbrx-instruct", "model": "DBRX Instruct", "creator": "Databricks", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 32, "rankingEligible": true, "overallRank": 96, "url": "https://benchlm.ai/models/dbrx-instruct", "markdownUrl": "https://benchlm.ai/md/models/dbrx-instruct.md", "id": 154, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "dbrx", "familyName": "DBRX", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "dbrx-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 32, "overallScore": 32, "rawOverallScore": 32, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 8.5, "coding": 60, "reasoning": null, "multimodalGrounded": null, "knowledge": 29.4, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 96, "categoryRanks": { "agentic": 98, "reasoning": 90, "multimodalGrounded": 107, "multilingual": 99 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-3-beta", "canonicalModelKey": "grok-3-beta", "model": "Grok 3 [Beta]", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 30, "rankingEligible": true, "overallRank": 97, "url": "https://benchlm.ai/models/grok-3-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-3-beta.md", "id": 149, "releaseDate": "2025-02-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-3", "familyName": "Grok 3", "variantType": "snapshot", "snapshotLabel": "beta", "baseFamilyModelKey": "grok-3-beta", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 30, "overallScore": 18, "rawOverallScore": 18, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 21, "coding": 28.2, "reasoning": 28.6, "multimodalGrounded": 9.4, "knowledge": 34.2, "multilingual": 1.8, "instructionFollowing": null, "math": 10.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 97, "categoryRanks": { "agentic": 81, "coding": 72, "reasoning": 73, "multimodalGrounded": 97, "knowledge": 83, "multilingual": 98, "instructionFollowing": 122, "math": 78 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-v3-1-reasoning", "canonicalModelKey": "deepseek-v3-1-reasoning", "model": "DeepSeek V3.1 (Reasoning)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 29, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/deepseek-v3-1-reasoning", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1-reasoning.md", "id": 155, "releaseDate": "2025-08-21", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-1", "familyName": "DeepSeek V3.1", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-1", "relatedModelKeys": [ "deepseek-v3-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 29, "overallScore": 15, "rawOverallScore": 15, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 32.9, "coding": 21, "reasoning": 26.7, "multimodalGrounded": 6.2, "knowledge": 13.4, "multilingual": 11.2, "instructionFollowing": 14.1, "math": 7.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 98, "categoryRanks": { "agentic": 70, "coding": 81, "reasoning": 76, "multimodalGrounded": 101, "knowledge": 100, "multilingual": 86, "instructionFollowing": 116, "math": 82 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 18.85, "tau2Bench": 37.4, "gdpvalAaNormalized": 5.6, "gdpvalAa": 612 }, "coding": { "aaCodingIndex": 29.71, "terminalBenchHard": 25, "aaSciCode": 39.1 }, "reasoning": { "lcr": 53.3, "critpt": 2 }, "multimodalGrounded": { "designArenaWebsite": 1168 }, "knowledge": { "artificialAnalysis": 27.71, "aaGpqaDiamond": 77.9, "aaHle": 13, "aaOmniscienceIndex": -28.4, "omniscienceAccuracy": 28.8, "omniscienceHallucinationRate": 80.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.5 }, "math": {} } }, { "slug": "o1-pro", "canonicalModelKey": "o1-pro", "model": "o1-pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 28, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/o1-pro", "markdownUrl": "https://benchlm.ai/md/models/o1-pro.md", "id": 141, "releaseDate": "2024-12-01", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1", "o1-preview" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 28, "overallScore": 26, "rawOverallScore": 26, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 16.2, "coding": 14.5, "reasoning": 33.5, "multimodalGrounded": 19.3, "knowledge": 60.8, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 99, "categoryRanks": { "agentic": 92, "reasoning": 67, "multimodalGrounded": 90, "multilingual": 100 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 79, "artificialAnalysis": 25.76 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "phi-4", "canonicalModelKey": "phi-4", "model": "Phi-4", "creator": "Microsoft", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "16K", "contextWindowTokens": 16000, "displayScore": 27, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/phi-4", "markdownUrl": "https://benchlm.ai/md/models/phi-4.md", "id": 128, "releaseDate": "2025-01-01", "market": null, "isRegional": false, "family": { "familyKey": "phi-4", "familyName": "Phi-4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "phi-4", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 27, "overallScore": 39, "rawOverallScore": 39, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 11.7, "coding": 48.1, "reasoning": null, "multimodalGrounded": 18.9, "knowledge": 32.8, "multilingual": 25.5, "instructionFollowing": null, "math": 78.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 100, "categoryRanks": { "agentic": 96, "reasoning": 91, "multimodalGrounded": 92, "multilingual": 82 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 0, "tau2Bench": 0 }, "coding": { "aaCodingIndex": 11.21, "terminalBenchHard": 3.8, "aaSciCode": 26 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 10.41, "aaGpqaDiamond": 57.5, "aaHle": 4.1, "aaOmniscienceIndex": -56.7, "omniscienceAccuracy": 13.2, "omniscienceHallucinationRate": 80.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 23.5 }, "math": {} } }, { "slug": "gpt-4-1-nano", "canonicalModelKey": "gpt-4-1-nano", "model": "GPT-4.1 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 27, "rankingEligible": true, "overallRank": 101, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md", "id": 121, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1", "gpt-4-1-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 27, "overallScore": 32, "rawOverallScore": 32, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": 22.9, "coding": 8.7, "reasoning": 67.4, "multimodalGrounded": 37.9, "knowledge": 29.1, "multilingual": 5.6, "instructionFollowing": 59.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 50.3, "multilingual": null, "instructionFollowing": 83.2, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 101, "categoryRanks": { "agentic": 77, "reasoning": 28, "multimodalGrounded": 78, "multilingual": 92, "instructionFollowing": 70 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 5.75, "tau2Bench": 17.3, "gdpvalAaNormalized": 0, "gdpvalAa": 318 }, "coding": { "aaCodingIndex": 11.17, "terminalBenchHard": 3.8, "aaSciCode": 25.9 }, "reasoning": { "lcr": 17, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 40.1, "designArenaWebsite": 1018 }, "knowledge": { "mmlu": 80.1, "gpqa": 50.3, "artificialAnalysis": 13.04, "aaGpqaDiamond": 51.2, "aaHle": 3.9, "aaOmniscienceIndex": -56.4, "omniscienceAccuracy": 13.3, "omniscienceHallucinationRate": 80.4 }, "multilingual": {}, "instructionFollowing": { "ifeval": 83.2, "aaIfBench": 32 }, "math": {}, "korean": {} } }, { "slug": "glm-4-5", "canonicalModelKey": "glm-4-5", "model": "GLM-4.5", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 25, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/glm-4-5", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5.md", "id": 164, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-5", "familyName": "GLM-4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 25, "overallScore": 7, "rawOverallScore": 7, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 22.9, "coding": 7.8, "reasoning": 19.8, "multimodalGrounded": 5.2, "knowledge": 11.7, "multilingual": null, "instructionFollowing": 8.5, "math": 7.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 102, "categoryRanks": { "agentic": 78, "coding": 94, "reasoning": 83, "multimodalGrounded": 103, "knowledge": 101, "multilingual": 101, "instructionFollowing": 119, "math": 81 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1215 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "llama-4-scout", "canonicalModelKey": "llama-4-scout", "model": "Llama 4 Scout", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "10M", "contextWindowTokens": 10000000, "displayScore": 25, "rankingEligible": true, "overallRank": 103, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md", "id": 151, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-scout", "familyName": "Llama 4 Scout", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-scout", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 25, "overallScore": 23, "rawOverallScore": 23, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 17.2, "coding": null, "reasoning": 41.1, "multimodalGrounded": 36.4, "knowledge": 15.4, "multilingual": 4.7, "instructionFollowing": 18.8, "math": 15.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 103, "categoryRanks": { "agentic": 89, "coding": 101, "reasoning": 62, "multimodalGrounded": 79, "knowledge": 97, "multilingual": 93, "instructionFollowing": 113, "math": 76 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 5.17, "tau2Bench": 15.5, "gdpvalAaNormalized": 0, "gdpvalAa": 269 }, "coding": { "aaCodingIndex": 6.68, "terminalBenchHard": 1.5, "aaSciCode": 17 }, "reasoning": { "lcr": 25.8, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 52.9, "designArenaWebsite": 796 }, "knowledge": { "artificialAnalysis": 13.52, "aaGpqaDiamond": 58.7, "aaHle": 4.3, "aaOmniscienceIndex": -52.4, "omniscienceAccuracy": 14.6, "omniscienceHallucinationRate": 78.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.5 }, "math": {} } }, { "slug": "nemotron-3-nano-30b", "canonicalModelKey": "nemotron-3-nano-30b", "model": "Nemotron 3 Nano 30B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 25, "rankingEligible": true, "overallRank": 104, "url": "https://benchlm.ai/models/nemotron-3-nano-30b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-30b.md", "id": 145, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-nano-30b", "familyName": "Nemotron 3 Nano 30B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-nano-30b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 25, "overallScore": 22, "rawOverallScore": 22, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 19.8, "coding": 16.8, "reasoning": 28.1, "multimodalGrounded": 12.5, "knowledge": 29.8, "multilingual": 38.3, "instructionFollowing": 40.3, "math": 37.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 104, "categoryRanks": { "agentic": 82, "coding": 84, "reasoning": 74, "multimodalGrounded": 95, "knowledge": 86, "multilingual": 71, "instructionFollowing": 95, "math": 63 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 8.48, "tau2Bench": 25.4, "gdpvalAaNormalized": 0, "gdpvalAa": 347 }, "coding": { "aaCodingIndex": 15.76, "terminalBenchHard": 12.1, "aaSciCode": 23 }, "reasoning": { "lcr": 6.7, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 13.17, "aaGpqaDiamond": 39.9, "aaHle": 4.6, "aaOmniscienceIndex": -69.2, "omniscienceAccuracy": 11.4, "omniscienceHallucinationRate": 90.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 37.5 }, "math": {} } }, { "slug": "llama-3-70b", "canonicalModelKey": "llama-3-70b", "model": "Llama 3 70B", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 25, "rankingEligible": true, "overallRank": 105, "url": "https://benchlm.ai/models/llama-3-70b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-70b.md", "id": 143, "releaseDate": "2024-04-18", "market": null, "isRegional": false, "family": { "familyKey": "llama-3-70b", "familyName": "Llama 3 70B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-3-70b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 25, "overallScore": 23, "rawOverallScore": 23, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 22, "coding": 2.6, "reasoning": 39.4, "multimodalGrounded": 25.8, "knowledge": 25.8, "multilingual": 26.2, "instructionFollowing": 36.6, "math": 37.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 105, "categoryRanks": { "agentic": 79, "coding": 98, "reasoning": 63, "multimodalGrounded": 86, "knowledge": 90, "multilingual": 81, "instructionFollowing": 102, "math": 62 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-v3-1", "canonicalModelKey": "deepseek-v3-1", "model": "DeepSeek V3.1", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 24, "rankingEligible": true, "overallRank": 106, "url": "https://benchlm.ai/models/deepseek-v3-1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1.md", "id": 166, "releaseDate": "2025-08-21", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-1", "familyName": "DeepSeek V3.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-1", "relatedModelKeys": [ "deepseek-v3-1-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 5, "rawOverallScore": 5, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 25.9, "coding": 15.9, "reasoning": 15.3, "multimodalGrounded": 3.7, "knowledge": 9.8, "multilingual": 7.5, "instructionFollowing": null, "math": 5.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 106, "categoryRanks": { "agentic": 74, "coding": 86, "reasoning": 85, "multimodalGrounded": 104, "knowledge": 103, "multilingual": 89, "instructionFollowing": 123, "math": 83 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 31.94, "tau2Bench": 34.8, "gdpvalAaNormalized": 28.7, "gdpvalAa": 1075 }, "coding": { "aaCodingIndex": 28.39, "terminalBenchHard": 24.2, "aaSciCode": 36.7 }, "reasoning": { "lcr": 45, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1168 }, "knowledge": { "artificialAnalysis": 28.13, "aaGpqaDiamond": 73.5, "aaHle": 6.3, "aaOmniscienceIndex": -41.1, "omniscienceAccuracy": 23.1, "omniscienceHallucinationRate": 83.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 37.8 }, "math": {} } }, { "slug": "gpt-4-turbo", "canonicalModelKey": "gpt-4-turbo", "model": "GPT-4 Turbo", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 24, "rankingEligible": true, "overallRank": 107, "url": "https://benchlm.ai/models/gpt-4-turbo", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-turbo.md", "id": 135, "releaseDate": "2023-11-06", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-turbo", "familyName": "GPT-4 Turbo", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-turbo", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 27, "rawOverallScore": 27, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 23.1, "coding": 12.6, "reasoning": 38.7, "multimodalGrounded": 31.2, "knowledge": 28.6, "multilingual": 22.4, "instructionFollowing": 47.6, "math": 39.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 107, "categoryRanks": { "agentic": 76, "coding": 89, "reasoning": 64, "multimodalGrounded": 84, "knowledge": 87, "multilingual": 84, "instructionFollowing": 85, "math": 61 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 30, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 21.49, "aaSciCode": 31.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 13.72, "aaHle": 3.3 }, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "gemini-1-0-pro", "canonicalModelKey": "gemini-1-0-pro", "model": "Gemini 1.0 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 24, "rankingEligible": true, "overallRank": 108, "url": "https://benchlm.ai/models/gemini-1-0-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-0-pro.md", "id": 146, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gemini-1-0-pro", "familyName": "Gemini 1.0 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-1-0-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 30, "rawOverallScore": 30, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 14.6, "coding": null, "reasoning": 27.4, "multimodalGrounded": 55.2, "knowledge": 25, "multilingual": 24.4, "instructionFollowing": 36.6, "math": 42.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 108, "categoryRanks": { "agentic": 93, "reasoning": 75, "multimodalGrounded": 63, "knowledge": 94, "multilingual": 83, "instructionFollowing": 103, "math": 58 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 31, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 11.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 8.5, "aaGpqaDiamond": 27.7, "aaHle": 4.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "z-1", "canonicalModelKey": "z-1", "model": "Z-1", "creator": "Z", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 23, "rankingEligible": true, "overallRank": 109, "url": "https://benchlm.ai/models/z-1", "markdownUrl": "https://benchlm.ai/md/models/z-1.md", "id": 138, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "z-1", "familyName": "Z-1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "z-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 23, "overallScore": 27, "rawOverallScore": 27, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 19.3, "coding": 21.3, "reasoning": 29.4, "multimodalGrounded": 22.4, "knowledge": 26, "multilingual": 40.9, "instructionFollowing": 47.6, "math": 31 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 109, "categoryRanks": { "agentic": 83, "coding": 79, "reasoning": 72, "multimodalGrounded": 87, "knowledge": 89, "multilingual": 68, "instructionFollowing": 86, "math": 70 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mistral-8x7b", "canonicalModelKey": "mistral-8x7b", "model": "Mistral 8x7B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 23, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/mistral-8x7b", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b.md", "id": 133, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-8x7b", "familyName": "Mistral 8x7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-8x7b", "relatedModelKeys": [ "mistral-8x7b-v0-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 23, "overallScore": 28, "rawOverallScore": 28, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 17.2, "coding": 18.8, "reasoning": 32.2, "multimodalGrounded": 18.2, "knowledge": 35.1, "multilingual": 39.1, "instructionFollowing": 40.3, "math": 46.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 110, "categoryRanks": { "agentic": 90, "coding": 83, "reasoning": 69, "multimodalGrounded": 93, "knowledge": 81, "multilingual": 70, "instructionFollowing": 96, "math": 54 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-3-haiku", "canonicalModelKey": "claude-3-haiku", "model": "Claude 3 Haiku", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 23, "rankingEligible": true, "overallRank": 111, "url": "https://benchlm.ai/models/claude-3-haiku", "markdownUrl": "https://benchlm.ai/md/models/claude-3-haiku.md", "id": 130, "releaseDate": "2024-03-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-haiku", "familyName": "Claude 3 Haiku", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-haiku", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 23, "overallScore": 30, "rawOverallScore": 30, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 18.3, "coding": 7.7, "reasoning": 37.4, "multimodalGrounded": 55.8, "knowledge": 25.4, "multilingual": 36.3, "instructionFollowing": 33, "math": 34.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 111, "categoryRanks": { "agentic": 86, "coding": 95, "reasoning": 65, "multimodalGrounded": 62, "knowledge": 92, "multilingual": 72, "instructionFollowing": 108, "math": 66 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 7.02, "tau2Bench": 21.1, "gdpvalAaNormalized": 0, "gdpvalAa": 378 }, "coding": { "aaCodingIndex": 6.72, "terminalBenchHard": 0.8, "aaSciCode": 18.6 }, "reasoning": { "lcr": 21, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 30.8 }, "knowledge": { "artificialAnalysis": 12.26, "aaGpqaDiamond": 37.4, "aaHle": 3.9, "aaOmniscienceIndex": -47.6, "omniscienceAccuracy": 17.2, "omniscienceHallucinationRate": 78.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.1 }, "math": {} } }, { "slug": "mixtral-8x22b-instruct-v0-1", "canonicalModelKey": "mixtral-8x22b-instruct-v0-1", "model": "Mixtral 8x22B Instruct v0.1", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 22, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/mixtral-8x22b-instruct-v0-1", "markdownUrl": "https://benchlm.ai/md/models/mixtral-8x22b-instruct-v0-1.md", "id": 158, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mixtral-8x22b", "familyName": "Mixtral 8x22B", "variantType": "instruct", "snapshotLabel": "v0.1", "baseFamilyModelKey": "mixtral-8x22b-instruct-v0-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 22, "overallScore": 25, "rawOverallScore": 25, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 7.6, "coding": 36.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 30.1, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 112, "categoryRanks": { "agentic": 99, "reasoning": 92, "multimodalGrounded": 108, "multilingual": 102 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": true, "multimodalGrounded": true, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "nemotron-4-15b", "canonicalModelKey": "nemotron-4-15b", "model": "Nemotron-4 15B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 22, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/nemotron-4-15b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-4-15b.md", "id": 140, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "nemotron-4-15b", "familyName": "Nemotron-4 15B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-4-15b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 22, "overallScore": 25, "rawOverallScore": 25, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 17.7, "coding": 20.7, "reasoning": 24.4, "multimodalGrounded": 20.9, "knowledge": 25.7, "multilingual": 40.1, "instructionFollowing": 44, "math": 32.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 113, "categoryRanks": { "agentic": 88, "coding": 82, "reasoning": 79, "multimodalGrounded": 89, "knowledge": 91, "multilingual": 69, "instructionFollowing": 92, "math": 68 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "moonshot-v1", "canonicalModelKey": "moonshot-v1", "model": "Moonshot v1", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 22, "rankingEligible": true, "overallRank": 114, "url": "https://benchlm.ai/models/moonshot-v1", "markdownUrl": "https://benchlm.ai/md/models/moonshot-v1.md", "id": 137, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "moonshot", "familyName": "Moonshot", "variantType": "snapshot", "snapshotLabel": "v1", "baseFamilyModelKey": "moonshot-v1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 22, "overallScore": 27, "rawOverallScore": 27, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 18.6, "coding": 21.2, "reasoning": 30.1, "multimodalGrounded": 26.3, "knowledge": 25.2, "multilingual": 32.7, "instructionFollowing": 36.6, "math": 31.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 114, "categoryRanks": { "agentic": 84, "coding": 80, "reasoning": 71, "multimodalGrounded": 85, "knowledge": 93, "multilingual": 79, "instructionFollowing": 104, "math": 69 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "nemotron-ultra-253b", "canonicalModelKey": "nemotron-ultra-253b", "model": "Nemotron Ultra 253B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 22, "rankingEligible": true, "overallRank": 115, "url": "https://benchlm.ai/models/nemotron-ultra-253b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-ultra-253b.md", "id": 132, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-ultra-253b", "familyName": "Nemotron Ultra 253B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-ultra-253b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 22, "overallScore": 28, "rawOverallScore": 28, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 18.6, "coding": 26.9, "reasoning": 26.6, "multimodalGrounded": 11.4, "knowledge": 24.9, "multilingual": 33.6, "instructionFollowing": 40.3, "math": 27.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 115, "categoryRanks": { "agentic": 85, "coding": 73, "reasoning": 77, "multimodalGrounded": 96, "knowledge": 95, "multilingual": 76, "instructionFollowing": 97, "math": 71 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 3.8, "tau2Bench": 11.4, "gdpvalAaNormalized": 0, "gdpvalAa": 238 }, "coding": { "aaCodingIndex": 13.09, "terminalBenchHard": 2.3, "aaSciCode": 34.7 }, "reasoning": { "lcr": 7.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 15.02, "aaGpqaDiamond": 72.8, "aaHle": 8.1, "aaOmniscienceIndex": -45.5, "omniscienceAccuracy": 19.9, "omniscienceHallucinationRate": 81.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38.2 }, "math": {} } }, { "slug": "glm-4-5-air", "canonicalModelKey": "glm-4-5-air", "model": "GLM-4.5-Air", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 18, "rankingEligible": true, "overallRank": 116, "url": "https://benchlm.ai/models/glm-4-5-air", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5-air.md", "id": 163, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-5-air", "familyName": "GLM-4.5-Air", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-5-air", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 18, "overallScore": 4, "rawOverallScore": 4, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 17.8, "coding": 12.5, "reasoning": 14.8, "multimodalGrounded": 3, "knowledge": 8.9, "multilingual": 2.9, "instructionFollowing": 5.4, "math": 3.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 116, "categoryRanks": { "agentic": 87, "coding": 90, "reasoning": 86, "multimodalGrounded": 105, "knowledge": 104, "multilingual": 96, "instructionFollowing": 120, "math": 84 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 21.01, "tau2Bench": 46.5, "gdpvalAaNormalized": 3, "gdpvalAa": 560 }, "coding": { "aaCodingIndex": 23.82, "terminalBenchHard": 20.5, "aaSciCode": 30.6 }, "reasoning": { "lcr": 43.7, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1192 }, "knowledge": { "artificialAnalysis": 23.17, "aaGpqaDiamond": 73.3, "aaHle": 6.8, "aaOmniscienceIndex": -62.5, "omniscienceAccuracy": 15.5, "omniscienceHallucinationRate": 92.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 37.6 }, "math": {} } }, { "slug": "llama-4-maverick", "canonicalModelKey": "llama-4-maverick", "model": "Llama 4 Maverick", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 17, "rankingEligible": true, "overallRank": 117, "url": "https://benchlm.ai/models/llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/models/llama-4-maverick.md", "id": 150, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-maverick", "familyName": "Llama 4 Maverick", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-maverick", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 17, "overallScore": 18, "rawOverallScore": 18, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 12.6, "coding": 8, "reasoning": 32.7, "multimodalGrounded": 34.6, "knowledge": 13.7, "multilingual": 4.7, "instructionFollowing": 22.7, "math": 10.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 117, "categoryRanks": { "agentic": 95, "coding": 93, "reasoning": 68, "multimodalGrounded": 81, "knowledge": 99, "multilingual": 94, "instructionFollowing": 112, "math": 79 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 38, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 7.22, "tau2Bench": 17.8, "gdpvalAaNormalized": 0, "gdpvalAa": 436 }, "coding": { "aaCodingIndex": 15.58, "terminalBenchHard": 6.8, "aaSciCode": 33.1 }, "reasoning": { "lcr": 46, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 62.1, "designArenaWebsite": 916 }, "knowledge": { "artificialAnalysis": 18.36, "aaGpqaDiamond": 67.1, "aaHle": 4.8, "aaOmniscienceIndex": -41.8, "omniscienceAccuracy": 24.3, "omniscienceHallucinationRate": 87.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 43 }, "math": {} } }, { "slug": "gemma-3-27b", "canonicalModelKey": "gemma-3-27b", "model": "Gemma 3 27B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 16, "rankingEligible": true, "overallRank": 118, "url": "https://benchlm.ai/models/gemma-3-27b", "markdownUrl": "https://benchlm.ai/md/models/gemma-3-27b.md", "id": 165, "releaseDate": "2025-03-12", "market": null, "isRegional": false, "family": { "familyKey": "gemma-3-27b", "familyName": "Gemma 3 27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemma-3-27b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 16, "overallScore": 9, "rawOverallScore": 9, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 12.8, "coding": 5.5, "reasoning": 19.9, "multimodalGrounded": 6.9, "knowledge": 16.6, "multilingual": 11.1, "instructionFollowing": null, "math": 13.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 118, "categoryRanks": { "agentic": 94, "coding": 96, "reasoning": 82, "multimodalGrounded": 99, "knowledge": 96, "multilingual": 87, "instructionFollowing": 124, "math": 77 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 30, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 3.51, "tau2Bench": 10.5, "gdpvalAaNormalized": 0, "gdpvalAa": 283 }, "coding": { "aaCodingIndex": 9.59, "terminalBenchHard": 3.8, "aaSciCode": 21.2 }, "reasoning": { "lcr": 5.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 48 }, "knowledge": { "artificialAnalysis": 10.31, "aaGpqaDiamond": 42.8, "aaHle": 4.7, "aaOmniscienceIndex": -65.9, "omniscienceAccuracy": 12.5, "omniscienceHallucinationRate": 89.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31.8 }, "math": {} } }, { "slug": "gpt-oss-20b", "canonicalModelKey": "gpt-oss-20b", "model": "GPT-OSS 20B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 16, "rankingEligible": true, "overallRank": 119, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md", "id": 167, "releaseDate": "2025-08-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-oss", "familyName": "GPT-OSS", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-oss-120b", "relatedModelKeys": [ "gpt-oss-120b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 16, "overallScore": 5, "rawOverallScore": 5, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 21.3, "coding": 9.3, "reasoning": 11.7, "multimodalGrounded": 1.5, "knowledge": 5.9, "multilingual": 4.6, "instructionFollowing": null, "math": 1.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 119, "categoryRanks": { "agentic": 80, "coding": 91, "reasoning": 88, "multimodalGrounded": 106, "knowledge": 105, "multilingual": 95, "instructionFollowing": 125, "math": 85 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 27.6, "apexAgentsAa": 0.7, "tau2Bench": 60.2, "gdpvalAaNormalized": 7.4, "gdpvalAa": 647 }, "coding": { "reactNativeEvals": 71, "aaCodingIndex": 18.53, "terminalBenchHard": 10.6, "aaSciCode": 34.4 }, "reasoning": { "lcr": 30.7, "critpt": 1.4 }, "multimodalGrounded": { "designArenaWebsite": 898 }, "knowledge": { "artificialAnalysis": 24.47, "aaGpqaDiamond": 68.8, "aaHle": 9.8, "aaOmniscienceIndex": -63.9, "omniscienceAccuracy": 15.5, "omniscienceHallucinationRate": 94.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 65.1 }, "math": {} } }, { "slug": "llama-4-behemoth", "canonicalModelKey": "llama-4-behemoth", "model": "Llama 4 Behemoth", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 11, "rankingEligible": true, "overallRank": 120, "url": "https://benchlm.ai/models/llama-4-behemoth", "markdownUrl": "https://benchlm.ai/md/models/llama-4-behemoth.md", "id": 156, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-behemoth", "familyName": "Llama 4 Behemoth", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-behemoth", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 11, "overallScore": 15, "rawOverallScore": 15, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 8.6, "coding": 3.9, "reasoning": 14.2, "multimodalGrounded": 31.9, "knowledge": 14.3, "multilingual": 13.1, "instructionFollowing": 26.5, "math": 18.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 120, "categoryRanks": { "agentic": 97, "coding": 97, "reasoning": 87, "multimodalGrounded": 83, "knowledge": 98, "multilingual": 85, "instructionFollowing": 111, "math": 75 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 37, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "nova-pro", "canonicalModelKey": "nova-pro", "model": "Nova Pro", "creator": "Amazon", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 10, "rankingEligible": true, "overallRank": 121, "url": "https://benchlm.ai/models/nova-pro", "markdownUrl": "https://benchlm.ai/md/models/nova-pro.md", "id": 162, "releaseDate": "2025-04-01", "market": null, "isRegional": false, "family": { "familyKey": "nova-pro", "familyName": "Nova Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nova-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 10, "overallScore": 9, "rawOverallScore": 9, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 4.8, "coding": 8.6, "reasoning": 18, "multimodalGrounded": 5.5, "knowledge": 10.3, "multilingual": 8.4, "instructionFollowing": null, "math": 9.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 121, "categoryRanks": { "agentic": 100, "coding": 92, "reasoning": 84, "multimodalGrounded": 102, "knowledge": 102, "multilingual": 88, "instructionFollowing": 126, "math": 80 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 31, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 4.68, "tau2Bench": 14, "gdpvalAaNormalized": 0, "gdpvalAa": 386 }, "coding": { "aaCodingIndex": 10.98, "terminalBenchHard": 6.1, "aaSciCode": 20.8 }, "reasoning": { "lcr": 19, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 44.3 }, "knowledge": { "artificialAnalysis": 13.48, "aaGpqaDiamond": 49.9, "aaHle": 3.4, "aaOmniscienceIndex": -47.6, "omniscienceAccuracy": 17, "omniscienceHallucinationRate": 77.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38.1 }, "math": {} } }, { "slug": "mistral-7b-v0-3", "canonicalModelKey": "mistral-7b-v0-3", "model": "Mistral 7B v0.3", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 4, "rankingEligible": true, "overallRank": 122, "url": "https://benchlm.ai/models/mistral-7b-v0-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-7b-v0-3.md", "id": 169, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-7b", "familyName": "Mistral 7B", "variantType": "snapshot", "snapshotLabel": "v0.3", "baseFamilyModelKey": "mistral-7b-v0-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 4, "overallScore": 3, "rawOverallScore": 3, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 0.7, "reasoning": 2.7, "multimodalGrounded": null, "knowledge": 4.9, "multilingual": 7.4, "instructionFollowing": 3.7, "math": 1.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 122, "categoryRanks": { "agentic": 101, "coding": 100, "reasoning": 89, "multimodalGrounded": 109, "knowledge": 106, "multilingual": 90, "instructionFollowing": 121, "math": 86 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mistral-8x7b-v0-2", "canonicalModelKey": "mistral-8x7b-v0-2", "model": "Mistral 8x7B v0.2", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 1, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/mistral-8x7b-v0-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b-v0-2.md", "id": 170, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-8x7b", "familyName": "Mistral 8x7B", "variantType": "snapshot", "snapshotLabel": "v0.2", "baseFamilyModelKey": "mistral-8x7b", "relatedModelKeys": [ "mistral-8x7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 1, "overallScore": 2, "rawOverallScore": 2, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 1, "reasoning": null, "multimodalGrounded": null, "knowledge": 2.4, "multilingual": 1.9, "instructionFollowing": null, "math": 1.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 123, "categoryRanks": { "agentic": 102, "coding": 99, "reasoning": 93, "multimodalGrounded": 110, "knowledge": 107, "multilingual": 97, "instructionFollowing": 127, "math": 87 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-5-pro", "canonicalModelKey": "gpt-5-5-pro", "model": "GPT-5.5 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 100, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md", "id": 25, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-5", "familyName": "GPT-5.5", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-5", "relatedModelKeys": [ "gpt-5-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 100, "overallScore": 100, "rawOverallScore": 100, "verifiedDisplayScore": 75, "displayCategoryScores": { "agentic": 100, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 100, "multilingual": null, "instructionFollowing": null, "math": 100 }, "verifiedDisplayCategoryScores": { "agentic": 90.1, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 57.2, "multilingual": null, "instructionFollowing": null, "math": 52.4 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "browseComp": 90.1 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "hle": 57.2, "hleNoTools": 43.1 }, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMath": 52.4 } } }, { "slug": "holo3-35b-a3b", "canonicalModelKey": "holo3-35b-a3b", "model": "Holo3-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 100, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-35b-a3b.md", "id": 3, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "holo3", "familyName": "Holo3", "variantType": "35b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-122b-a10b", "relatedModelKeys": [ "holo3-122b-a10b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-30b-a3b" }, "scores": { "displayScore": 100, "overallScore": 100, "rawOverallScore": 100, "verifiedDisplayScore": 83, "displayCategoryScores": { "agentic": 100, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 82.6, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "osWorldVerified": 82.56 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-122b-a10b", "canonicalModelKey": "holo3-122b-a10b", "model": "Holo3-122B-A10B", "creator": "H Company", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 94, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/holo3-122b-a10b.md", "id": 13, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "holo3", "familyName": "Holo3", "variantType": "122b-a10b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-122b-a10b", "relatedModelKeys": [ "holo3-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "holo2-235b-a22b" }, "scores": { "displayScore": 94, "overallScore": 94, "rawOverallScore": 94, "verifiedDisplayScore": 79, "displayCategoryScores": { "agentic": 93.9, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 78.9, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "osWorldVerified": 78.85 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mimo-v2-5-pro", "canonicalModelKey": "mimo-v2-5-pro", "model": "MiMo-V2.5-Pro", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 85, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md", "id": 88, "releaseDate": "2026-04-22", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-5", "familyName": "MiMo-V2.5", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-5", "relatedModelKeys": [ "mimo-v2-5", "mimo-v2-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "mimo-v2-pro" }, "scores": { "displayScore": 85, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": 85.5, "coding": 80.1, "reasoning": null, "multimodalGrounded": null, "knowledge": 87.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 68.4, "coding": 57.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 48, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 63.8, "gdpvalAa": 1571, "tau3Bench": 72.9, "terminalBench2": 68.4, "aaAgenticIndex": 67.44, "tau2Bench": 94.2, "gdpvalAaNormalized": 53.6, "apexAgentsAa": 2.4, "gertLabs": 62.7 }, "coding": { "swePro": 57.2, "terminalBench2": 68.4, "aaCodingIndex": 45.53, "terminalBenchHard": 43.2, "aaSciCode": 50.2 }, "reasoning": { "lcr": 73.3, "critpt": 4 }, "multimodalGrounded": { "designArenaWebsite": 1312 }, "knowledge": { "hle": 48, "hleNoTools": 34, "artificialAnalysis": 53.83, "aaGpqaDiamond": 86.6, "aaHle": 33.8, "aaOmniscienceIndex": 3.6, "omniscienceAccuracy": 22.6, "omniscienceHallucinationRate": 24.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 79.9 }, "math": {} } }, { "slug": "mimo-v2-pro", "canonicalModelKey": "mimo-v2-pro", "model": "MiMo-V2-Pro", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 84, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mimo-v2-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-pro.md", "id": 6, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-pro", "familyName": "MiMo-V2-Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-pro", "relatedModelKeys": [ "mimo-v2-flash", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 84, "overallScore": 84, "rawOverallScore": 84, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 77.5, "coding": 95.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 87.8, "multilingual": null, "instructionFollowing": 52.5, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 82 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 57.8, "aaAgenticIndex": 62.8, "tau2Bench": 95, "gdpvalAaNormalized": 45.3, "gdpvalAa": 1405, "gertLabs": 36.68 }, "coding": { "sweVerified": 78, "aaCodingIndex": 41.43, "terminalBenchHard": 40.9, "aaSciCode": 42.5 }, "reasoning": { "lcr": 60.7, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 49.2, "aaGpqaDiamond": 87, "aaHle": 28.3, "aaOmniscienceIndex": 4.9, "omniscienceAccuracy": 26.8, "omniscienceHallucinationRate": 29.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 68.8 }, "math": {} } }, { "slug": "mimo-v2-omni", "canonicalModelKey": "mimo-v2-omni", "model": "MiMo-V2-Omni", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 84, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mimo-v2-omni", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-omni.md", "id": 24, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-omni", "familyName": "MiMo-V2-Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-omni", "relatedModelKeys": [ "mimo-v2-flash", "mimo-v2-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 84, "overallScore": 84, "rawOverallScore": 84, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 91, "reasoning": null, "multimodalGrounded": 71.6, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 45.2, "aaAgenticIndex": 58.56, "tau2Bench": 91.2, "gdpvalAaNormalized": 40.9, "gdpvalAa": 1317 }, "coding": { "sweVerified": 74.8, "aaCodingIndex": 35.46, "terminalBenchHard": 34.8, "aaSciCode": 36.7 }, "reasoning": { "lcr": 66.7, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 69.9 }, "knowledge": { "artificialAnalysis": 43.4, "aaGpqaDiamond": 82.8, "aaHle": 19.9, "aaOmniscienceIndex": -17.4, "omniscienceAccuracy": 18.7, "omniscienceHallucinationRate": 44.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 53.5 }, "math": {} } }, { "slug": "composer-2-5", "canonicalModelKey": "composer-2-5", "model": "Composer 2.5", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 81, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md", "id": 46, "releaseDate": "2026-05-18", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "composer-2-5", "relatedModelKeys": [ "composer-2", "composer-2-fast" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "composer-2" }, "scores": { "displayScore": 81, "overallScore": 81, "rawOverallScore": 81, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 81.5, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 69.3, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 69.3 }, "coding": { "terminalBench2": 69.3, "sweMultilingual": 79.8, "cursorBench31": 63.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "muse-spark", "canonicalModelKey": "muse-spark", "model": "Muse Spark", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 80, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-spark", "markdownUrl": "https://benchlm.ai/md/models/muse-spark.md", "id": 103, "releaseDate": "2026-04-08", "market": null, "isRegional": false, "family": { "familyKey": "muse-spark", "familyName": "Muse Spark", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "muse-spark", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 80, "overallScore": 69, "rawOverallScore": 69, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 74, "coding": 82.7, "reasoning": 57, "multimodalGrounded": 78.2, "knowledge": 92.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 59, "coding": 61.7, "reasoning": 42.5, "multimodalGrounded": 82.2, "knowledge": 50.4, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multimodalGrounded": 19 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 21, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 59, "tau2Bench": 91.5, "deepSearchQa": 74.8, "cyberGym": 43.5, "clawEval": 63.8, "aaAgenticIndex": 61.99, "gdpvalAaNormalized": 45.9, "gdpvalAa": 1417 }, "coding": { "sweVerified": 77.4, "swePro": 52.4, "liveCodeBenchPro": 80, "vibeCodeBench": 19.674, "aaCodingIndex": 47.47, "terminalBenchHard": 45.5, "aaSciCode": 51.5 }, "reasoning": { "arcAgi2": 42.5, "lcr": 69.7, "critpt": 11.3 }, "multimodalGrounded": { "charxiv": 86.4, "mmmuPro": 80.4, "erqa": 64.7, "simpleVqa": 71.3, "screenSpotPro": 84.1, "zeroBench": 33, "medXpertQaMm": 78.4, "gdpvalAa": 1444, "aaMmmuPro": 80.5 }, "knowledge": { "gpqaDiamond": 89.5, "hle": 50.4, "hleNoTools": 42.8, "healthBenchHard": 42.8, "medXpertQaText": 52.6, "artificialAnalysis": 52.15, "aaGpqaDiamond": 88.4, "aaHle": 39.9, "aaOmniscienceIndex": 4.1, "omniscienceAccuracy": 44.6, "omniscienceHallucinationRate": 73.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": {} } }, { "slug": "qwen3-6-max-preview", "canonicalModelKey": "qwen3-6-max-preview", "model": "Qwen 3.6 Max (preview)", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 78, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-6-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-max-preview.md", "id": 75, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-max", "familyName": "Qwen 3.6 Max", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "qwen3-6-max-preview", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-5-plus" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 72, "rawOverallScore": 72, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": 79.9, "coding": 75.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 69.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 65.4, "coding": 54.1, "reasoning": null, "multimodalGrounded": null, "knowledge": 73.9, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 65.4, "qwenClawBench": 59, "qwenWebBench": 1532, "aaAgenticIndex": 64.83, "tau2Bench": 95.9, "gdpvalAaNormalized": 50.2, "gdpvalAa": 1504 }, "coding": { "swePro": 57.3, "sciCode": 47, "nl2Repo": 42.9, "terminalBench2": 65.4, "aaCodingIndex": 44.92, "terminalBenchHard": 43.9, "aaSciCode": 46.9 }, "reasoning": { "lcr": 69.7, "critpt": 3.7 }, "multimodalGrounded": {}, "knowledge": { "superGpqa": 73.9, "artificialAnalysis": 51.81, "aaGpqaDiamond": 88.8, "aaHle": 28.9, "aaOmniscienceIndex": 10.2, "omniscienceAccuracy": 37.7, "omniscienceHallucinationRate": 44.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.6 }, "math": {} } }, { "slug": "mistral-medium-3-5-128b", "canonicalModelKey": "mistral-medium-3-5-128b", "model": "Mistral Medium 3.5 128B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 78, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-medium-3-5-128b", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3-5-128b.md", "id": 17, "releaseDate": "2026-04-29", "market": null, "isRegional": false, "family": { "familyKey": "mistral-medium-3-5", "familyName": "Mistral Medium 3.5", "variantType": "128b", "snapshotLabel": null, "baseFamilyModelKey": "mistral-medium-3-5-128b", "relatedModelKeys": [ "mistral-medium-3" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 95, "rawOverallScore": 95, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": null, "coding": 84.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 77.6, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau3Bench": 91.4, "aaAgenticIndex": 53.16, "tau2Bench": 94.2, "gdpvalAaNormalized": 33.4, "gdpvalAa": 1168, "gertLabs": 39.1 }, "coding": { "sweVerified": 77.6, "aaCodingIndex": 35.42, "terminalBenchHard": 33.3, "aaSciCode": 39.6 }, "reasoning": { "lcr": 61, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 64.9 }, "knowledge": { "artificialAnalysis": 39.23, "aaGpqaDiamond": 74.8, "aaHle": 12.8, "aaOmniscienceIndex": -36.3, "omniscienceAccuracy": 25.1, "omniscienceHallucinationRate": 82 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 68.8 }, "math": {} } }, { "slug": "interfaze-beta", "canonicalModelKey": "interfaze-beta", "model": "Interfaze Beta", "creator": "Interfaze", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 77, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/interfaze-beta", "markdownUrl": "https://benchlm.ai/md/models/interfaze-beta.md", "id": 10, "releaseDate": "2026-05-11", "market": null, "isRegional": false, "family": { "familyKey": "interfaze", "familyName": "Interfaze", "variantType": "beta", "snapshotLabel": "beta", "baseFamilyModelKey": "interfaze-beta", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 77, "overallScore": 77, "rawOverallScore": 77, "verifiedDisplayScore": 81, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 61.6, "knowledge": 92.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 71.1, "knowledge": 89.9, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "spider2Lite": 52.9 }, "reasoning": {}, "multimodalGrounded": { "ocrBenchV2": 70.7, "olmOcr": 85.7, "refcocoAvg": 82.1, "voxPopuliWer": 2.4, "mmmuPro": 71.1 }, "knowledge": { "gpqa": 89.9, "gpqaDiamond": 89.9, "mmmlu": 90.9 }, "multilingual": {}, "instructionFollowing": { "sobValueAcc": 79.5 }, "math": {} } }, { "slug": "grok-4-3", "canonicalModelKey": "grok-4-3", "model": "Grok 4.3", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 74, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md", "id": 87, "releaseDate": "2026-04-30", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-3", "familyName": "Grok 4.3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 74, "overallScore": 71, "rawOverallScore": 71, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": null, "coding": 64.3, "reasoning": null, "multimodalGrounded": 73.9, "knowledge": 73.6, "multilingual": null, "instructionFollowing": 86.9, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 47.3, "reasoning": null, "multimodalGrounded": 78.1, "knowledge": 53.9, "multilingual": null, "instructionFollowing": 81.3, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 23 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 97.7, "gdpvalAaNormalized": 49.8, "aaAgenticIndex": 65.89, "apexAgentsAa": 17, "gdpvalAa": 1495, "gertLabs": 43.86 }, "coding": { "sciCode": 47.3, "terminalBenchHard": 37.9, "aaCodingIndex": 41.03, "aaSciCode": 47.3 }, "reasoning": { "lcr": 64.3, "critpt": 8 }, "multimodalGrounded": { "mmmuPro": 78.1, "designArenaWebsite": 1252, "aaMmmuPro": 78.1 }, "knowledge": { "artificialAnalysis": 53.2, "gpqa": 90.1, "hle": 35, "omniscienceAccuracy": 34.6, "omniscienceHallucinationRate": 25, "aaGpqaDiamond": 90.1, "aaHle": 35, "aaOmniscienceIndex": 18.3 }, "multilingual": {}, "instructionFollowing": { "ifBench": 81.3, "aaIfBench": 81.3 }, "math": {} } }, { "slug": "composer-2", "canonicalModelKey": "composer-2", "model": "Composer 2", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 73, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md", "id": 89, "releaseDate": "2026-03-19", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "composer-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 73, "overallScore": 73, "rawOverallScore": 73, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": 65.3, "coding": 80.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 61.7, "coding": 58, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 61.7 }, "coding": { "sweMultilingual": 73.7, "sweRebench": 58, "reactNativeEvals": 96.1, "terminalBench2": 61.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mimo-v2-5", "canonicalModelKey": "mimo-v2-5", "model": "MiMo-V2.5", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md", "id": 70, "releaseDate": "2026-04-22", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-5", "familyName": "MiMo-V2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-5", "relatedModelKeys": [ "mimo-v2-5-pro", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "mimo-v2-omni" }, "scores": { "displayScore": 71, "overallScore": 73, "rawOverallScore": 73, "verifiedDisplayScore": 65, "displayCategoryScores": { "agentic": 72.7, "coding": 70.3, "reasoning": null, "multimodalGrounded": 70, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 65.8, "coding": 56.1, "reasoning": null, "multimodalGrounded": 78.9, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multimodalGrounded": 30 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 9, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "clawEval": 62.3, "mmClawBench": 23.8, "terminalBench2": 65.8, "gertLabs": 46.89 }, "coding": { "swePro": 56.1, "terminalBench2": 65.8 }, "reasoning": {}, "multimodalGrounded": { "videoMmeWithSub": 87.7, "charxiv": 81, "mmmuPro": 77.9, "designArenaWebsite": 1306 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "step-3-7-flash", "canonicalModelKey": "step-3-7-flash", "model": "Step 3.7 Flash", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 70, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md", "id": 239, "releaseDate": "2026-05-29", "market": null, "isRegional": false, "family": { "familyKey": "step-3-7-flash", "familyName": "Step 3.7 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-3-7-flash", "relatedModelKeys": [ "step-3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "step-3-5-flash" }, "scores": { "displayScore": 70, "overallScore": 71, "rawOverallScore": 71, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 70.6, "coding": 72.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 65.9, "coding": 56.3, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 59.5, "browseComp": 75.82, "deepSearchQa": 92.82, "gdpvalAaNormalized": 40, "toolathlon": 49.5, "clawEval": 67.1, "hleWithTools": 47.2, "gertLabs": 51.57, "aaAgenticIndex": 59.53, "tau2Bench": 98.5, "gdpvalAa": 1300 }, "coding": { "swePro": 56.3, "terminalBench2": 59.5, "aaCodingIndex": 37.09, "terminalBenchHard": 35.6, "aaSciCode": 40 }, "reasoning": { "lcr": 63.7, "critpt": 2.3 }, "multimodalGrounded": { "simpleVqa": 79.2, "vStar": 95.3, "aaMmmuPro": 75.3, "designArenaWebsite": 1227 }, "knowledge": { "artificialAnalysis": 42.59, "aaGpqaDiamond": 80.9, "aaHle": 19.9, "aaOmniscienceIndex": -37.5, "omniscienceAccuracy": 25.4, "omniscienceHallucinationRate": 84.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.3 }, "math": {} } }, { "slug": "grok-4-20-multi-agent-beta", "canonicalModelKey": "grok-4-20-multi-agent-beta", "model": "Grok 4.20 Multi-agent", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 70, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-4-20-multi-agent-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-multi-agent-beta.md", "id": 8, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-20", "familyName": "Grok 4.20", "variantType": "multi-agent", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-20-beta", "relatedModelKeys": [ "grok-4-20-beta" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 70, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 62.8, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 100, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 2 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-4-mini", "canonicalModelKey": "gpt-5-4-mini", "model": "GPT-5.4 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 68, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md", "id": 81, "releaseDate": "2026-03-17", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-pro", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-5-mini" }, "scores": { "displayScore": 68, "overallScore": 62, "rawOverallScore": 62, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": 72.6, "coding": 75.7, "reasoning": 15.2, "multimodalGrounded": 71.2, "knowledge": 80, "multilingual": null, "instructionFollowing": 72.2, "math": 92.2 }, "verifiedDisplayCategoryScores": { "agentic": 65.6, "coding": null, "reasoning": null, "multimodalGrounded": 76.6, "knowledge": 41.5, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 51 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 19, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 60, "osWorldVerified": 72.1, "mcpAtlas": 57.7, "toolathlon": 42.9, "tau2Bench": 83.3, "aaAgenticIndex": 58.88, "apexAgentsAa": 28.2, "gdpvalAaNormalized": 46.9, "gdpvalAa": 1438 }, "coding": { "vibeCodeBench": 47.969, "aaCodingIndex": 51.48, "terminalBenchHard": 52.3, "aaSciCode": 49.9 }, "reasoning": { "lcr": 69.3, "critpt": 10 }, "multimodalGrounded": { "mmmuPro": 76.6, "mmmuProPython": 78, "aaMmmuPro": 73.3 }, "knowledge": { "gpqa": 88, "hle": 41.5, "hleNoTools": 28.2, "artificialAnalysis": 48.9, "aaGpqaDiamond": 87.5, "aaHle": 26.6, "aaOmniscienceIndex": -18.7, "omniscienceAccuracy": 37.5, "omniscienceHallucinationRate": 89.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.3 }, "math": {} } }, { "slug": "gemma-4-31b", "canonicalModelKey": "gemma-4-31b", "model": "Gemma 4 31B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 64, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md", "id": 65, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "31b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-26b-a4b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 64, "overallScore": 58, "rawOverallScore": 58, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": 54, "reasoning": 54.7, "multimodalGrounded": 71.8, "knowledge": 72.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 41.6, "reasoning": null, "multimodalGrounded": 76.9, "knowledge": 55.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 34 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 40.94, "tau2Bench": 59.9, "gdpvalAaNormalized": 30.7, "gdpvalAa": 1113, "gertLabs": 35.26 }, "coding": { "sweRebench": 41.6, "reactNativeEvals": 75.2, "aaCodingIndex": 38.71, "terminalBenchHard": 36.4, "aaSciCode": 43.4 }, "reasoning": { "lcr": 62, "critpt": 1.4 }, "multimodalGrounded": { "mmmuPro": 76.9, "aaMmmuPro": 73.4 }, "knowledge": { "gpqa": 84.3, "mmluPro": 85.2, "hle": 26.5, "hleNoTools": 19.5, "artificialAnalysis": 39.18, "aaGpqaDiamond": 85.7, "aaHle": 22.7, "aaOmniscienceIndex": -45.4, "omniscienceAccuracy": 19.9, "omniscienceHallucinationRate": 81.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.6 }, "math": {} } }, { "slug": "exaone-4-0-32b", "canonicalModelKey": "exaone-4-0-32b", "model": "Exaone 4.0 32B", "creator": "LG AI Research", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 63, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/exaone-4-0-32b", "markdownUrl": "https://benchlm.ai/md/models/exaone-4-0-32b.md", "id": 2, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-4", "familyName": "Exaone 4.0", "variantType": "32b", "snapshotLabel": null, "baseFamilyModelKey": "exaone-4-0-32b", "relatedModelKeys": [ "exaone-4-0-1-2b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 81, "rawOverallScore": 81, "verifiedDisplayScore": 83, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 81.1, "multilingual": null, "instructionFollowing": null, "math": 79.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 81.8, "multilingual": null, "instructionFollowing": null, "math": 85.3 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.36, "tau2Bench": 4.1, "gdpvalAaNormalized": 0, "gdpvalAa": 328 }, "coding": { "aaCodingIndex": 9.42, "terminalBenchHard": 1.5, "aaSciCode": 25.2 }, "reasoning": { "lcr": 8, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "mmluPro": 81.8, "artificialAnalysis": 11.66, "aaGpqaDiamond": 62.8, "aaHle": 4.9, "aaOmniscienceIndex": -62.3, "omniscienceAccuracy": 10.4, "omniscienceHallucinationRate": 81 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.5 }, "math": { "aime2025": 85.3 }, "korean": {} } }, { "slug": "glm-5v-turbo", "canonicalModelKey": "glm-5v-turbo", "model": "GLM-5V-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 62, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-5v-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5v-turbo.md", "id": 102, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "vision-turbo", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning", "glm-5-1", "glm-5-turbo" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 62, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 60.4, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 53.8, "aaAgenticIndex": 61.07, "tau2Bench": 98.5, "gdpvalAaNormalized": 41.4, "gdpvalAa": 1328, "gertLabs": 30.76 }, "coding": { "aaCodingIndex": 36.22, "terminalBenchHard": 32.6, "aaSciCode": 43.5 }, "reasoning": { "lcr": 61, "critpt": 0.6 }, "multimodalGrounded": { "aaMmmuPro": 72.8 }, "knowledge": { "artificialAnalysis": 42.85, "aaGpqaDiamond": 80.9, "aaHle": 15.8, "aaOmniscienceIndex": -19, "omniscienceAccuracy": 29.1, "omniscienceHallucinationRate": 67.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 61.1 }, "math": {} } }, { "slug": "gpt-5-4-nano", "canonicalModelKey": "gpt-5-4-nano", "model": "GPT-5.4 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 59, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md", "id": 127, "releaseDate": "2026-03-17", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-pro", "gpt-5-4-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-5-nano" }, "scores": { "displayScore": 59, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": 47.3, "coding": 72.9, "reasoning": 14.7, "multimodalGrounded": 52.8, "knowledge": 74.1, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 42.9, "coding": null, "reasoning": null, "multimodalGrounded": 66.1, "knowledge": 37.7, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 46.3, "osWorldVerified": 39, "mcpAtlas": 56.1, "toolathlon": 35.5, "tau2Bench": 76, "aaAgenticIndex": 47.6, "apexAgentsAa": 24.9, "gdpvalAaNormalized": 34.8, "gdpvalAa": 1195 }, "coding": { "vibeCodeBench": 26.097, "aaCodingIndex": 43.91, "terminalBenchHard": 42.4, "aaSciCode": 46.9 }, "reasoning": { "lcr": 66, "critpt": 9.3 }, "multimodalGrounded": { "mmmuPro": 66.1, "mmmuProPython": 69.5, "aaMmmuPro": 65.4 }, "knowledge": { "gpqa": 82.8, "hle": 37.7, "hleNoTools": 24.3, "artificialAnalysis": 43.98, "aaGpqaDiamond": 81.7, "aaHle": 26.5, "aaOmniscienceIndex": -29.5, "omniscienceAccuracy": 25.4, "omniscienceHallucinationRate": 73.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": {} } }, { "slug": "mellum2-12b-a2-5b-thinking", "canonicalModelKey": "mellum2-12b-a2-5b-thinking", "model": "Mellum2-12B-A2.5B-Thinking", "creator": "JetBrains", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mellum2-12b-a2-5b-thinking", "markdownUrl": "https://benchlm.ai/md/models/mellum2-12b-a2-5b-thinking.md", "id": 252, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "mellum2-12b-a2-5b", "familyName": "Mellum2 12B-A2.5B", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "mellum2-12b-a2-5b-instruct", "relatedModelKeys": [ "mellum2-12b-a2-5b-instruct" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 59, "overallScore": 59, "rawOverallScore": 59, "verifiedDisplayScore": 67, "displayCategoryScores": { "agentic": null, "coding": 73.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 42.7, "multilingual": null, "instructionFollowing": 34.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 69.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 57.6, "multilingual": null, "instructionFollowing": 76.5, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 106 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 45.6 }, "coding": { "liveCodeBench": 69.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluRedux": 86.2, "gpqa": 57.6, "gpqaDiamond": 57.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 76.5 }, "math": {} } }, { "slug": "hy3-preview", "canonicalModelKey": "hy3-preview", "model": "Hy3 Preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 58, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md", "id": 111, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "hy3", "familyName": "Hy3", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "hy3-preview", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 58, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 57.1, "coding": 62.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 60.1, "multilingual": null, "instructionFollowing": 33.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 54.4, "coding": 60, "reasoning": null, "multimodalGrounded": null, "knowledge": 46.7, "multilingual": null, "instructionFollowing": 63.1, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 107 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 54.4, "tau2Bench": 92.7, "gdpvalAaNormalized": 36.8, "aaAgenticIndex": 55.67, "gdpvalAa": 1236, "gertLabs": 36.91 }, "coding": { "sweVerified": 74.4, "terminalBench2": 54.4, "terminalBenchHard": 34.1, "sciCode": 41.2, "aaCodingIndex": 36.46, "aaSciCode": 41.2 }, "reasoning": { "lcr": 54.7, "critpt": 4.6 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 41.85, "gpqa": 87.2, "gpqaDiamond": 87.2, "hle": 25.5, "omniscienceAccuracy": 28, "omniscienceHallucinationRate": 86.9, "aaGpqaDiamond": 86.7, "aaHle": 25.5, "aaOmniscienceIndex": -34.6 }, "multilingual": {}, "instructionFollowing": { "ifBench": 63.1, "aaIfBench": 63.1 }, "math": {} } }, { "slug": "zaya1-8b", "canonicalModelKey": "zaya1-8b", "model": "ZAYA1-8B", "creator": "Zyphra", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 57, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md", "id": 30, "releaseDate": "2026-05-05", "market": null, "isRegional": false, "family": { "familyKey": "zaya1", "familyName": "ZAYA1", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "zaya1-8b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 62.7, "multilingual": null, "instructionFollowing": 44.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 73.1, "multilingual": null, "instructionFollowing": 74, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 89 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 39.22 }, "coding": { "liveCodeBenchV6": 65.8 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 71, "gpqaDiamond": 71, "mmluPro": 74.2 }, "multilingual": {}, "instructionFollowing": { "ifeval": 85.58, "ifBench": 52.56 }, "math": { "aime2026": 89.1, "hmmtFeb2026": 71.6, "imoAnswerBench": 59.3, "apex": 32.2 } } }, { "slug": "gemma-4-26b-a4b", "canonicalModelKey": "gemma-4-26b-a4b", "model": "Gemma 4 26B A4B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-26b-a4b.md", "id": 74, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "26b-a4b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 56, "rawOverallScore": 56, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": null, "coding": 65.6, "reasoning": 18.8, "multimodalGrounded": 66.3, "knowledge": 62.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 73.8, "knowledge": 49.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 49 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 32.15, "tau2Bench": 43.6, "gdpvalAaNormalized": 25.7, "gdpvalAa": 1014 }, "coding": { "aaCodingIndex": 22.44, "terminalBenchHard": 13.6, "aaSciCode": 40 }, "reasoning": { "lcr": 55.7, "critpt": 0 }, "multimodalGrounded": { "mmmuPro": 73.8, "aaMmmuPro": 69.2 }, "knowledge": { "mmluPro": 82.6, "hle": 17.2, "hleNoTools": 8.7, "artificialAnalysis": 31.21, "aaGpqaDiamond": 79.2, "aaHle": 18.3, "aaOmniscienceIndex": -48.1, "omniscienceAccuracy": 18.2, "omniscienceHallucinationRate": 80.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 72.4 }, "math": {} } }, { "slug": "zaya1-74b-preview", "canonicalModelKey": "zaya1-74b-preview", "model": "ZAYA1-74B-Preview", "creator": "Zyphra", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/models/zaya1-74b-preview.md", "id": 105, "releaseDate": "2026-05-07", "market": null, "isRegional": false, "family": { "familyKey": "zaya1", "familyName": "ZAYA1", "variantType": "74b-preview", "snapshotLabel": "preview", "baseFamilyModelKey": "zaya1-74b-preview", "relatedModelKeys": [ "zaya1-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 54, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": null, "coding": 59.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 45.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 53.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 64.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Airline": 56.1 }, "coding": { "liveCodeBenchV6": 65.7, "sweVerified": 53.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluPro": 68.1, "gpqa": 57.3, "gpqaDiamond": 57.3 }, "multilingual": {}, "instructionFollowing": {}, "math": { "aime2026": 76.4 } } }, { "slug": "mistral-small-4-reasoning", "canonicalModelKey": "mistral-small-4-reasoning", "model": "Mistral Small 4 (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-small-4-reasoning", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4-reasoning.md", "id": 49, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-small-4", "familyName": "Mistral Small 4", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "mistral-small-4", "relatedModelKeys": [ "mistral-small-4" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 62, "rawOverallScore": 62, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 57.9, "reasoning": null, "multimodalGrounded": 42.1, "knowledge": 68.8, "multilingual": null, "instructionFollowing": null, "math": 77.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 25.87, "tau2Bench": 41.2, "gdpvalAaNormalized": 18, "gdpvalAa": 859 }, "coding": { "aaCodingIndex": 24.27, "terminalBenchHard": 17.4, "aaSciCode": 38 }, "reasoning": { "lcr": 44.7, "critpt": 0.3 }, "multimodalGrounded": { "aaMmmuPro": 56.8 }, "knowledge": { "artificialAnalysis": 27.8, "aaGpqaDiamond": 76.9, "aaHle": 9.5, "aaOmniscienceIndex": -29.9, "omniscienceAccuracy": 22.1, "omniscienceHallucinationRate": 66.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.2 }, "math": {} } }, { "slug": "laguna-m-1", "canonicalModelKey": "laguna-m-1", "model": "Laguna M.1", "creator": "Poolside", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 51, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md", "id": 118, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "laguna", "familyName": "Laguna", "variantType": "m-1", "snapshotLabel": null, "baseFamilyModelKey": "laguna-m-1", "relatedModelKeys": [ "laguna-xs-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 51, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": 52, "displayCategoryScores": { "agentic": 31.5, "coding": 72.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 45.8, "coding": 58.6, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 45.8 }, "coding": { "sweVerified": 74.6, "sweMultilingual": 63.1, "swePro": 49.2, "terminalBench2": 45.8 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "k-exaone", "canonicalModelKey": "k-exaone", "model": "K-Exaone", "creator": "LG AI Research", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 50, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/k-exaone", "markdownUrl": "https://benchlm.ai/md/models/k-exaone.md", "id": 131, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-frontier", "familyName": "K-Exaone", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "k-exaone", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 54, "rawOverallScore": 54, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 50.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 38.14, "tau2Bench": 74.3, "gdpvalAaNormalized": 16.2, "gdpvalAa": 824 }, "coding": { "aaCodingIndex": 27.03, "terminalBenchHard": 22.7, "aaSciCode": 35.6 }, "reasoning": { "lcr": 55.7, "critpt": 1.1 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 32.12, "aaGpqaDiamond": 78.3, "aaHle": 13.1, "aaOmniscienceIndex": -57.9, "omniscienceAccuracy": 16.5, "omniscienceHallucinationRate": 89.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 64.7 }, "math": {}, "korean": {} } }, { "slug": "nemotron-3-nano-omni-30b-a3b", "canonicalModelKey": "nemotron-3-nano-omni-30b-a3b", "model": "Nemotron 3 Nano Omni 30B A3B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 48, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/nemotron-3-nano-omni-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-omni-30b-a3b.md", "id": 52, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-nano-omni", "familyName": "Nemotron 3 Nano Omni", "variantType": "30b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-nano-omni-30b-a3b", "relatedModelKeys": [ "nemotron-3-nano-30b", "nemotron-3-super-120b-a12b", "nemotron-3-super-100b", "nemotron-3-ultra-500b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": null, "coding": 40.9, "reasoning": null, "multimodalGrounded": 47.5, "knowledge": 68.3, "multilingual": null, "instructionFollowing": 71.3, "math": 74.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 53.5, "reasoning": null, "multimodalGrounded": 76.3, "knowledge": 75.5, "multilingual": null, "instructionFollowing": 74.2, "math": 82.1 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 52 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 15, "verifiedBenchmarkCount": 15, "rankableBenchmarkCount": 15, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "osWorld": 47.4, "tau2Bench": 45.3, "aaAgenticIndex": 23.87, "gdpvalAaNormalized": 13.1, "gdpvalAa": 762 }, "coding": { "liveCodeBench": 63.2, "sciCode": 32, "aaCodingIndex": 14.81, "terminalBenchHard": 8.3, "aaSciCode": 27.8 }, "reasoning": { "lcr": 35.7, "critpt": 0 }, "multimodalGrounded": { "mmmu": 70.8, "mmLongBenchDoc": 57.5, "charxiv": 76.25, "screenSpotPro": 57.8, "videoMmeNoSub": 72.2, "ai2dTest": 88.5, "refcocoAvg": 90.5, "aaMmmuPro": 53.2 }, "knowledge": { "mmluPro": 77.3, "gpqa": 72.2, "gpqaDiamond": 72.2, "artificialAnalysis": 21.43, "aaGpqaDiamond": 46.9, "aaHle": 5.3, "aaOmniscienceIndex": -56, "omniscienceAccuracy": 14.8, "omniscienceHallucinationRate": 83.1 }, "multilingual": {}, "instructionFollowing": { "ifBench": 74.2, "aaIfBench": 63.2 }, "math": { "aime2025": 82.1 } } }, { "slug": "gemma-4-12b", "canonicalModelKey": "gemma-4-12b", "model": "Gemma 4 12B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 48, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemma-4-12b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-12b.md", "id": 251, "releaseDate": "2026-06-03", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "12b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 53, "rawOverallScore": 53, "verifiedDisplayScore": 65, "displayCategoryScores": { "agentic": null, "coding": 65.9, "reasoning": 10.1, "multimodalGrounded": 58.1, "knowledge": 71.7, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 72, "reasoning": 43.4, "multimodalGrounded": 69.1, "knowledge": 77.8, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 12, "verifiedBenchmarkCount": 12, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "aaAgenticIndex": 24.63, "tau2Bench": 36.3, "gdpvalAaNormalized": 18.8, "gdpvalAa": 875 }, "coding": { "liveCodeBench": 72, "aaCodingIndex": 24.85, "terminalBenchHard": 18.2, "aaSciCode": 38.2 }, "reasoning": { "bbh": 53, "mrcrv2": 43.4, "lcr": 55.3, "critpt": 0 }, "multimodalGrounded": { "mmmuPro": 69.1, "mathVision": 79.7, "medXpertQaMm": 48.7, "aaMmmuPro": 69.7 }, "knowledge": { "gpqa": 78.8, "gpqaDiamond": 78.8, "mmluPro": 77.2, "hleNoTools": 5.2, "mmmlu": 83.4, "artificialAnalysis": 29.17, "aaGpqaDiamond": 75.3, "aaHle": 14.8, "aaOmniscienceIndex": -51.9, "omniscienceAccuracy": 16, "omniscienceHallucinationRate": 80.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.5 }, "math": { "aime2026": 77.5 } } }, { "slug": "ternary-bonsai-8b", "canonicalModelKey": "ternary-bonsai-8b", "model": "Ternary Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 44, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-8b.md", "id": 80, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-4b", "ternary-bonsai-1-7b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 44, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 41.6, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 54.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 81 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-8b-a1b", "canonicalModelKey": "lfm2-5-8b-a1b", "model": "LFM2.5-8B-A1B", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-8b-a1b.md", "id": 240, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-8b-a1b", "familyName": "LFM2.5-8B-A1B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-8b-a1b", "relatedModelKeys": [ "lfm2-5-1-2b-thinking", "lfm2-5-350m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 63.7, "math": 36.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 79.5, "math": 59.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 62, "math": 65 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 49.73, "gdpvalAaNormalized": 0, "gdpvalAa": 255, "aaAgenticIndex": 5.36, "tau2Bench": 16.1 }, "coding": { "aaCodingIndex": 5.62, "terminalBenchHard": 4.5, "aaSciCode": 7.8 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "aaGpqaDiamond": 51.3, "aaHle": 6.9, "aaOmniscienceIndex": -33.3, "omniscienceAccuracy": 9.4, "omniscienceHallucinationRate": 47, "artificialAnalysis": 14.19 }, "multilingual": {}, "instructionFollowing": { "ifeval": 91.84, "ifBench": 56.47, "aaIfBench": 55.6 }, "math": { "math500": 88.76, "aime2025": 42.53, "aime2026": 50 } } }, { "slug": "mistral-medium-3", "canonicalModelKey": "mistral-medium-3", "model": "Mistral Medium 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-medium-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3.md", "id": 106, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-medium-3", "familyName": "Mistral Medium 3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-medium-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 47, "rawOverallScore": 47, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 20.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 59.9, "multilingual": null, "instructionFollowing": 82.1, "math": 82.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 32 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 13.74, "tau2Bench": 24.3, "gdpvalAaNormalized": 4.2, "gdpvalAa": 585 }, "coding": { "aaCodingIndex": 13.56, "terminalBenchHard": 3.8, "aaSciCode": 33.1 }, "reasoning": { "lcr": 28, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 53, "designArenaWebsite": 1124 }, "knowledge": { "artificialAnalysis": 18.76, "aaGpqaDiamond": 57.8, "aaHle": 4.3, "aaOmniscienceIndex": -31.5, "omniscienceAccuracy": 18.3, "omniscienceHallucinationRate": 60.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.3 }, "math": {} } }, { "slug": "deepseek-v4-pro-base", "canonicalModelKey": "deepseek-v4-pro-base", "model": "DeepSeek V4 Pro Base", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 41, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepseek-v4-pro-base", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-base.md", "id": 82, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "base", "snapshotLabel": "pro-base", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 41, "rawOverallScore": 41, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 24, "multimodalGrounded": null, "knowledge": 49.2, "multilingual": 67.8, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 51.5, "multimodalGrounded": null, "knowledge": 63.4, "multilingual": 84.4, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 62, "multilingual": 37 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 24, "verifiedBenchmarkCount": 24, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": {}, "coding": { "bigCodeBench": 59.2, "humaneval": 76.8 }, "reasoning": { "bbh": 87.5, "drop": 88.7, "hellaswag": 88, "winogrande": 81.5, "cluewsc": 85.2, "longBenchV2": 51.5 }, "multimodalGrounded": {}, "knowledge": { "agieval": 83.1, "mmlu": 90.1, "mmluRedux": 90.8, "mmluPro": 73.5, "mmmlu": 90.3, "cEval": 93.1, "cmmlu": 90.8, "multiLoKo": 51.1, "simpleQa": 55.2, "superGpqa": 53.9, "factsParametric": 62.6, "triviaQa": 85.6 }, "multilingual": { "mgsm": 84.4 }, "instructionFollowing": {}, "math": { "gsm8k": 92.6, "mathBenchmark": 64.5, "cmath": 90.9 } } }, { "slug": "mistral-small-4", "canonicalModelKey": "mistral-small-4", "model": "Mistral Small 4", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 41, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-small-4", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4.md", "id": 66, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-small-4", "familyName": "Mistral Small 4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-small-4", "relatedModelKeys": [ "mistral-small-4-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 36.9, "multilingual": null, "instructionFollowing": 48.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 84 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 25.87, "tau2Bench": 41.2, "gdpvalAaNormalized": 18, "gdpvalAa": 859 }, "coding": { "aaCodingIndex": 24.27, "terminalBenchHard": 17.4, "aaSciCode": 38 }, "reasoning": { "lcr": 44.7, "critpt": 0.3 }, "multimodalGrounded": { "aaMmmuPro": 56.8 }, "knowledge": { "artificialAnalysis": 27.8, "aaGpqaDiamond": 76.9, "aaHle": 9.5, "aaOmniscienceIndex": -29.9, "omniscienceAccuracy": 22.1, "omniscienceHallucinationRate": 66.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.2 }, "math": {} } }, { "slug": "grok-3-mini", "canonicalModelKey": "grok-3-mini", "model": "Grok 3 Mini", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 41, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-3-mini", "markdownUrl": "https://benchlm.ai/md/models/grok-3-mini.md", "id": 134, "releaseDate": "2025-02-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-3-mini", "familyName": "Grok 3 Mini", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-3-mini", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 41, "rawOverallScore": 41, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 36.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 48.9, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 63 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "sarvam-30b", "canonicalModelKey": "sarvam-30b", "model": "Sarvam 30B", "creator": "Sarvam", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 40, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sarvam-30b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-30b.md", "id": 136, "releaseDate": "2026-03-06", "market": null, "isRegional": false, "family": { "familyKey": "sarvam-30b", "familyName": "Sarvam 30B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "sarvam-30b", "relatedModelKeys": [ "sarvam-105b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "sarvam-m" }, "scores": { "displayScore": 40, "overallScore": 53, "rawOverallScore": 53, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 24.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 76.6, "multilingual": null, "instructionFollowing": null, "math": 81.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "math": 21 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": true } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 11.5, "tau2Bench": 34.5, "gdpvalAaNormalized": 0, "gdpvalAa": 359 }, "coding": { "aaCodingIndex": 7.92, "terminalBenchHard": 2.3, "aaSciCode": 19.2 }, "reasoning": { "lcr": 0, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 12.34, "aaGpqaDiamond": 63.3, "aaHle": 7, "aaOmniscienceIndex": -72, "omniscienceAccuracy": 12.7, "omniscienceHallucinationRate": 97 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 26.5 }, "math": {} } }, { "slug": "command-a-plus", "canonicalModelKey": "command-a-plus", "model": "Command A+", "creator": "Cohere", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 39, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md", "id": 86, "releaseDate": "2026-05-20", "market": null, "isRegional": false, "family": { "familyKey": "command-a", "familyName": "Command A", "variantType": "plus", "snapshotLabel": null, "baseFamilyModelKey": "command-a-plus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 39, "overallScore": 33, "rawOverallScore": 33, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 32.8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 59.8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multimodalGrounded": 82 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 80.7, "aaAgenticIndex": 40.9, "gdpvalAaNormalized": 20.9, "gdpvalAa": 919 }, "coding": { "terminalBenchHard": 25, "aaCodingIndex": 29.28, "aaSciCode": 37.8 }, "reasoning": { "lcr": 46, "critpt": 0.3 }, "multimodalGrounded": { "mmmu": 75.1, "mmmuPro": 63, "charxiv": 52.7, "aaMmmuPro": 63.2 }, "knowledge": { "artificialAnalysis": 37.16, "aaGpqaDiamond": 76.1, "aaHle": 11.4, "aaOmniscienceIndex": -4, "omniscienceAccuracy": 8.9, "omniscienceHallucinationRate": 14.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.9 }, "math": {} } }, { "slug": "laguna-xs-2", "canonicalModelKey": "laguna-xs-2", "model": "Laguna XS.2", "creator": "Poolside", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 37, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md", "id": 147, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "laguna", "familyName": "Laguna", "variantType": "xs-2", "snapshotLabel": null, "baseFamilyModelKey": "laguna-m-1", "relatedModelKeys": [ "laguna-m-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 37, "overallScore": 37, "rawOverallScore": 37, "verifiedDisplayScore": 45, "displayCategoryScores": { "agentic": 10, "coding": 66.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 35.7, "coding": 55.1, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 35.7 }, "coding": { "sweVerified": 69.9, "sweMultilingual": 57.7, "swePro": 46.3, "terminalBench2": 35.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemma-4-e4b", "canonicalModelKey": "gemma-4-e4b", "model": "Gemma 4 E4B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 37, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemma-4-e4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e4b.md", "id": 139, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "e4b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 37, "overallScore": 44, "rawOverallScore": 44, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 41.4, "reasoning": null, "multimodalGrounded": 29.1, "knowledge": 48.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 6.92, "tau2Bench": 20.8, "gdpvalAaNormalized": 0, "gdpvalAa": 303 }, "coding": { "aaCodingIndex": 13.7, "terminalBenchHard": 8.3, "aaSciCode": 24.4 }, "reasoning": { "lcr": 30.7, "critpt": 0.6 }, "multimodalGrounded": { "aaMmmuPro": 51.4 }, "knowledge": { "gpqa": 58.6, "mmluPro": 69.4, "artificialAnalysis": 18.76, "aaGpqaDiamond": 57.6, "aaHle": 3.7, "aaOmniscienceIndex": -20, "omniscienceAccuracy": 8.6, "omniscienceHallucinationRate": 31.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.2 }, "math": {} } }, { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 36, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md", "id": 153, "releaseDate": "2026-04-21", "market": null, "isRegional": false, "family": { "familyKey": "ling-2-6", "familyName": "Ling 2.6", "variantType": "flash", "snapshotLabel": null, "baseFamilyModelKey": "ling-2-6-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 36, "overallScore": 36, "rawOverallScore": 36, "verifiedDisplayScore": 41, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 44.9, "multilingual": null, "instructionFollowing": 14.6, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 27, "reasoning": null, "multimodalGrounded": null, "knowledge": 59, "multilingual": null, "instructionFollowing": 57, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 115 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 86, "gdpvalAa": 785, "aaAgenticIndex": 38.06, "gdpvalAaNormalized": 14.2 }, "coding": { "sciCode": 27, "aaCodingIndex": 23.17, "terminalBenchHard": 21.2, "aaSciCode": 27.1 }, "reasoning": { "lcr": 25, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 26.16, "gpqa": 59, "aaGpqaDiamond": 59.3, "aaHle": 6.2, "aaOmniscienceIndex": -65.7, "omniscienceAccuracy": 15.4, "omniscienceHallucinationRate": 95.8 }, "multilingual": {}, "instructionFollowing": { "ifBench": 57, "aaIfBench": 57.4 }, "math": {} } }, { "slug": "granite-4-0-1b", "canonicalModelKey": "granite-4-0-1b", "model": "Granite-4.0-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 32, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-1b.md", "id": 157, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-1b", "familyName": "Granite 4.0 1B", "variantType": "dense", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-h-1b", "relatedModelKeys": [ "granite-4-0-h-1b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 32, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 42.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multilingual": 103, "instructionFollowing": 93 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 7.6, "tau2Bench": 22.8, "gdpvalAaNormalized": 0, "gdpvalAa": 255 }, "coding": { "aaCodingIndex": 2.89, "terminalBenchHard": 0, "aaSciCode": 8.7 }, "reasoning": { "lcr": 4, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 7.34, "aaGpqaDiamond": 28.1, "aaHle": 5.1, "aaOmniscienceIndex": -81.8, "omniscienceAccuracy": 6.1, "omniscienceHallucinationRate": 93.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 20.5 }, "math": {} } }, { "slug": "deepseek-v4-flash-base", "canonicalModelKey": "deepseek-v4-flash-base", "model": "DeepSeek V4 Flash Base", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 29, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepseek-v4-flash-base", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-base.md", "id": 110, "releaseDate": "2026-04-24", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4", "familyName": "DeepSeek V4", "variantType": "base", "snapshotLabel": "flash-base", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-pro-base", "deepseek-v4-flash", "deepseek-v4-flash-high", "deepseek-v4-flash-max", "deepseek-v4-pro", "deepseek-v4-pro-high", "deepseek-v4-pro-max" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 29, "overallScore": 29, "rawOverallScore": 29, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 11, "multimodalGrounded": null, "knowledge": 30.1, "multilingual": 71.4, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 44.7, "multimodalGrounded": null, "knowledge": 52.2, "multilingual": 85.7, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 85, "multilingual": 29 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 24, "verifiedBenchmarkCount": 24, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": {}, "coding": { "bigCodeBench": 56.8, "humaneval": 69.5 }, "reasoning": { "bbh": 86.9, "drop": 88.6, "hellaswag": 85.7, "winogrande": 79.5, "cluewsc": 82.2, "longBenchV2": 44.7 }, "multimodalGrounded": {}, "knowledge": { "agieval": 82.6, "mmlu": 88.7, "mmluRedux": 89.4, "mmluPro": 68.3, "mmmlu": 88.8, "cEval": 92.1, "cmmlu": 90.4, "multiLoKo": 42.2, "simpleQa": 30.1, "superGpqa": 46.5, "factsParametric": 33.9, "triviaQa": 82.8 }, "multilingual": { "mgsm": 85.7 }, "instructionFollowing": {}, "math": { "gsm8k": 90.8, "mathBenchmark": 57.4, "cmath": 93.6 } } }, { "slug": "qwen3-5-flash", "canonicalModelKey": "qwen3-5-flash", "model": "Qwen3.5 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 28, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-flash.md", "id": 94, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-flash", "familyName": "Qwen3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-flash", "relatedModelKeys": [ "qwen3-5-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 28, "overallScore": 11, "rawOverallScore": 11, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 16.5, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 46.5, "math": 10.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 88 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ternary-bonsai-1-7b", "canonicalModelKey": "ternary-bonsai-1-7b", "model": "Ternary Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 28, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-1-7b.md", "id": 109, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "1-7b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-8b", "ternary-bonsai-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 28, "overallScore": 28, "rawOverallScore": 28, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 33, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 11.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 117 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mellum2-12b-a2-5b-instruct", "canonicalModelKey": "mellum2-12b-a2-5b-instruct", "model": "Mellum2-12B-A2.5B-Instruct", "creator": "JetBrains", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 27, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mellum2-12b-a2-5b-instruct", "markdownUrl": "https://benchlm.ai/md/models/mellum2-12b-a2-5b-instruct.md", "id": 253, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "mellum2-12b-a2-5b", "familyName": "Mellum2 12B-A2.5B", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "mellum2-12b-a2-5b-instruct", "relatedModelKeys": [ "mellum2-12b-a2-5b-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 27, "overallScore": 27, "rawOverallScore": 27, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": 30.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 17.2, "multilingual": null, "instructionFollowing": 32.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 37.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 40.9, "multilingual": null, "instructionFollowing": 75.8, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 109 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 44.2 }, "coding": { "liveCodeBench": 37.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluRedux": 78.1, "gpqa": 40.9, "gpqaDiamond": 40.9 }, "multilingual": {}, "instructionFollowing": { "ifeval": 75.8 }, "math": {} } }, { "slug": "claude-opus-4-6-thinking", "canonicalModelKey": "claude-opus-4-6-thinking", "model": "Claude Opus 4.6 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 24, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-opus-4-6-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6-thinking.md", "id": 228, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-6", "familyName": "Claude Opus 4.6", "variantType": "reasoning", "snapshotLabel": "adaptive", "baseFamilyModelKey": "claude-opus-4-6", "relatedModelKeys": [ "claude-opus-4-6" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 67.58, "apexAgentsAa": 33, "tau2Bench": 92.1, "gdpvalAaNormalized": 55.9, "gdpvalAa": 1619 }, "coding": { "vibeCodeBench": 53.498, "aaCodingIndex": 48.09, "terminalBenchHard": 46.2, "aaSciCode": 51.9 }, "reasoning": { "lcr": 70.7, "critpt": 12.6 }, "multimodalGrounded": { "aaMmmuPro": 75.4 }, "knowledge": { "artificialAnalysis": 52.95, "aaGpqaDiamond": 89.6, "aaHle": 36.7, "aaOmniscienceIndex": 13.5, "omniscienceAccuracy": 46.4, "omniscienceHallucinationRate": 61.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 53.1 }, "math": {} } }, { "slug": "qwen2-5-vl-32b", "canonicalModelKey": "qwen2-5-vl-32b", "model": "Qwen2.5-VL-32B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 24, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen2-5-vl-32b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-vl-32b.md", "id": 107, "releaseDate": "2025-01-26", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-vl-32b", "familyName": "Qwen2.5-VL-32B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-vl-32b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 32, "rawOverallScore": 32, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 23.7, "knowledge": 37, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemma-4-e2b", "canonicalModelKey": "gemma-4-e2b", "model": "Gemma 4 E2B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 24, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemma-4-e2b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e2b.md", "id": 161, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "e2b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 29, "rawOverallScore": 29, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 31.1, "reasoning": null, "multimodalGrounded": 14.4, "knowledge": 25.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 6.92, "tau2Bench": 20.8, "gdpvalAaNormalized": 0, "gdpvalAa": 270 }, "coding": { "aaCodingIndex": 9, "terminalBenchHard": 3, "aaSciCode": 20.9 }, "reasoning": { "lcr": 15, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 44.6 }, "knowledge": { "gpqa": 43.4, "mmluPro": 60, "artificialAnalysis": 15.21, "aaGpqaDiamond": 43.3, "aaHle": 4.8, "aaOmniscienceIndex": -24, "omniscienceAccuracy": 6.7, "omniscienceHallucinationRate": 32.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38 }, "math": {} } }, { "slug": "bonsai-1-7b", "canonicalModelKey": "bonsai-1-7b", "model": "1-bit Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 24, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-1-7b.md", "id": 160, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "1-7b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-8b", "bonsai-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 24, "overallScore": 24, "rawOverallScore": 24, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 24, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 128 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 23, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md", "id": 174, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-7", "familyName": "Claude Opus 4.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-7", "relatedModelKeys": [ "claude-opus-4-7-max", "claude-opus-4-6", "claude-opus-4-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-opus-4-6" }, "scores": { "displayScore": 23, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 64.64, "tau2Bench": 74, "gdpvalAaNormalized": 58.6, "gdpvalAa": 1672, "gertLabs": 65.59 }, "coding": { "vibeCodeBench": 71.003, "reactNativeEvals": 82.8, "aaCodingIndex": 53.07, "terminalBenchHard": 54.5, "aaSciCode": 50.1 }, "reasoning": { "lcr": 67, "critpt": 5.1 }, "multimodalGrounded": { "aaMmmuPro": 76.4, "designArenaWebsite": 1338 }, "knowledge": { "artificialAnalysis": 51.82, "aaGpqaDiamond": 88.5, "aaHle": 31.2, "aaOmniscienceIndex": 14.2, "omniscienceAccuracy": 43.5, "omniscienceHallucinationRate": 51.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 43.6 }, "math": {} } }, { "slug": "ternary-bonsai-4b", "canonicalModelKey": "ternary-bonsai-4b", "model": "Ternary Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 23, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-4b.md", "id": 120, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-8b", "ternary-bonsai-1-7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 23, "overallScore": 23, "rawOverallScore": 23, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 24, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 18.7, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 114 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "bonsai-8b", "canonicalModelKey": "bonsai-8b", "model": "1-bit Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 23, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-8b.md", "id": 126, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-4b", "bonsai-1-7b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 23, "overallScore": 23, "rawOverallScore": 23, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 31.7, "multimodalGrounded": null, "knowledge": 0.5, "multilingual": null, "instructionFollowing": 46.9, "math": 22 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 87 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-opus-4-5-thinking", "canonicalModelKey": "claude-opus-4-5-thinking", "model": "Claude Opus 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 21, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-opus-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5-thinking.md", "id": 230, "releaseDate": "2025-11-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-5", "familyName": "Claude Opus 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-opus-4-5", "relatedModelKeys": [ "claude-opus-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 21, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 59.64, "tau2Bench": 89.5, "gdpvalAaNormalized": 47.3, "gdpvalAa": 1446 }, "coding": { "vibeCodeBench": 20.63, "aaCodingIndex": 47.83, "terminalBenchHard": 47, "aaSciCode": 49.5 }, "reasoning": { "lcr": 74, "critpt": 4.6 }, "multimodalGrounded": { "aaMmmuPro": 74, "designArenaWebsite": 1292 }, "knowledge": { "artificialAnalysis": 49.73, "aaGpqaDiamond": 86.6, "aaHle": 28.4, "aaOmniscienceIndex": 13.3, "omniscienceAccuracy": 45.7, "omniscienceHallucinationRate": 59.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 58 }, "math": {} } }, { "slug": "glm-5-turbo", "canonicalModelKey": "glm-5-turbo", "model": "GLM-5-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 20, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-5-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5-turbo.md", "id": 204, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "turbo", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 20, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 55.8, "aaAgenticIndex": 66.13, "tau2Bench": 98.5, "gdpvalAaNormalized": 49.7, "gdpvalAa": 1493 }, "coding": { "aaCodingIndex": 36.77, "terminalBenchHard": 33.3, "aaSciCode": 43.6 }, "reasoning": { "lcr": 60.7, "critpt": 0.3 }, "multimodalGrounded": { "designArenaWebsite": 1322 }, "knowledge": { "artificialAnalysis": 46.76, "aaGpqaDiamond": 84.7, "aaHle": 25.4, "aaOmniscienceIndex": -15.1, "omniscienceAccuracy": 29, "omniscienceHallucinationRate": 62.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.2 }, "math": {} } }, { "slug": "gpt-5-2-instant", "canonicalModelKey": "gpt-5-2-instant", "model": "GPT-5.2 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 19, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-2-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-instant.md", "id": 179, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "instant", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2", "gpt-5-2-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 19, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-2-pro", "canonicalModelKey": "gpt-5-2-pro", "model": "GPT-5.2 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 19, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-2-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-pro.md", "id": 177, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2", "gpt-5-2-instant" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 19, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 31, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-3-instant", "canonicalModelKey": "gpt-5-3-instant", "model": "GPT-5.3 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 18, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-3-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-instant.md", "id": 178, "releaseDate": "2026-03-03", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3", "familyName": "GPT-5.3", "variantType": "instant", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-instant", "relatedModelKeys": [ "gpt-5-3-codex" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 18, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 35, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-3-codex-spark", "canonicalModelKey": "gpt-5-3-codex-spark", "model": "GPT-5.3-Codex-Spark", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 17, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-3-codex-spark", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex-spark.md", "id": 180, "releaseDate": "2026-02-12", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3-codex", "familyName": "GPT-5.3 Codex", "variantType": "spark", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-codex", "relatedModelKeys": [ "gpt-5-3-codex" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 17, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-1-codex", "canonicalModelKey": "gpt-5-1-codex", "model": "GPT-5.1-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 17, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-1-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex.md", "id": 231, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1-codex", "familyName": "GPT-5.1-Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1-codex", "relatedModelKeys": [ "gpt-5-1-codex-max" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 17, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 50.68, "tau2Bench": 83, "gdpvalAaNormalized": 34.5, "gdpvalAa": 1191, "gertLabs": 49.68 }, "coding": { "vibeCodeBench": 13.115, "aaCodingIndex": 36.62, "terminalBenchHard": 34.8, "aaSciCode": 40.2 }, "reasoning": { "lcr": 67.3, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 72.5, "designArenaWebsite": 1206 }, "knowledge": { "artificialAnalysis": 43.11, "aaGpqaDiamond": 86, "aaHle": 23.4, "aaOmniscienceIndex": -6, "omniscienceAccuracy": 39.2, "omniscienceHallucinationRate": 74.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70 }, "math": {} } }, { "slug": "bonsai-4b", "canonicalModelKey": "bonsai-4b", "model": "1-bit Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 17, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-4b.md", "id": 148, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-8b", "bonsai-1-7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 17, "overallScore": 17, "rawOverallScore": 17, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 18.1, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 9.5, "math": 21.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 118 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-4-1-fast-reasoning", "canonicalModelKey": "grok-4-1-fast-reasoning", "model": "Grok 4.1 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 16, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-4-1-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast-reasoning.md", "id": 235, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1-fast", "familyName": "Grok 4.1 Fast", "variantType": "reasoning", "snapshotLabel": "reasoning", "baseFamilyModelKey": "grok-4-1-fast", "relatedModelKeys": [ "grok-4-1-fast" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 16, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 49.31, "tau2Bench": 93.3, "gdpvalAaNormalized": 27.3, "gdpvalAa": 1045 }, "coding": { "vibeCodeBench": 1.2, "aaCodingIndex": 30.9, "terminalBenchHard": 24.2, "aaSciCode": 44.2 }, "reasoning": { "lcr": 68, "critpt": 2.9 }, "multimodalGrounded": { "aaMmmuPro": 63.3 }, "knowledge": { "artificialAnalysis": 38.61, "aaGpqaDiamond": 85.3, "aaHle": 17.6, "aaOmniscienceIndex": -28.7, "omniscienceAccuracy": 25.3, "omniscienceHallucinationRate": 72.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 52.7 }, "math": {} } }, { "slug": "glm-4-6", "canonicalModelKey": "glm-4-6", "model": "GLM-4.6", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 14, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-4-6", "markdownUrl": "https://benchlm.ai/md/models/glm-4-6.md", "id": 234, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-6", "familyName": "GLM-4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-6", "relatedModelKeys": [ "glm-4-7" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 14, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 42.89, "tau2Bench": 76.9, "gdpvalAaNormalized": 24.3, "gdpvalAa": 985 }, "coding": { "vibeCodeBench": 3.09, "aaCodingIndex": 30.23, "terminalBenchHard": 28.8, "aaSciCode": 33.1 }, "reasoning": { "lcr": 26.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 30.24, "aaGpqaDiamond": 63.2, "aaHle": 5.2, "aaOmniscienceIndex": -31.6, "omniscienceAccuracy": 20.8, "omniscienceHallucinationRate": 66.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.7 }, "math": {} } }, { "slug": "grok-4-fast-reasoning", "canonicalModelKey": "grok-4-fast-reasoning", "model": "Grok 4 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 14, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-4-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-fast-reasoning.md", "id": 236, "releaseDate": "2025-09-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-fast", "familyName": "Grok 4 Fast", "variantType": "reasoning", "snapshotLabel": "reasoning", "baseFamilyModelKey": "grok-4-fast-reasoning", "relatedModelKeys": [ "grok-4" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 14, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 39.51, "tau2Bench": 65.8, "gdpvalAaNormalized": 25.7, "gdpvalAa": 1015 }, "coding": { "vibeCodeBench": 0, "aaCodingIndex": 27.36, "terminalBenchHard": 18.9, "aaSciCode": 44.2 }, "reasoning": { "lcr": 64.7, "critpt": 2.9 }, "multimodalGrounded": { "aaMmmuPro": 61.8 }, "knowledge": { "artificialAnalysis": 35.06, "aaGpqaDiamond": 84.7, "aaHle": 17, "aaOmniscienceIndex": -28.4, "omniscienceAccuracy": 22.6, "omniscienceHallucinationRate": 66 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 50.5 }, "math": {} } }, { "slug": "trinity-large-preview", "canonicalModelKey": "trinity-large-preview", "model": "Trinity-Large-Preview", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 12, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/trinity-large-preview", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-preview.md", "id": 175, "releaseDate": "2026-01-27", "market": null, "isRegional": false, "family": { "familyKey": "trinity-large", "familyName": "Trinity Large", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "trinity-large-thinking", "relatedModelKeys": [ "trinity-large-thinking" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 12, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 42.61, "tau2Bench": 90.1, "gdpvalAaNormalized": 18.2, "gdpvalAa": 864 }, "coding": { "aaCodingIndex": 27.19, "terminalBenchHard": 22.7, "aaSciCode": 36.1 }, "reasoning": { "lcr": 33, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1181 }, "knowledge": { "mmlu": 87.2, "mmluProArcee": 75.2, "gpqaDiamond": 63.3, "artificialAnalysis": 31.87, "aaGpqaDiamond": 75.2, "aaHle": 14.7, "aaOmniscienceIndex": -44.2, "omniscienceAccuracy": 22.8, "omniscienceHallucinationRate": 86.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 56.3 }, "math": { "aime2025Arcee": 24 } } }, { "slug": "trinity-large-thinking", "canonicalModelKey": "trinity-large-thinking", "model": "Trinity-Large-Thinking", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 12, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md", "id": 116, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "trinity-large", "familyName": "Trinity Large", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "trinity-large-thinking", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 12, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 129 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 90.1, "aaAgenticIndex": 42.61, "gdpvalAaNormalized": 18.2, "gdpvalAa": 864, "gertLabs": 32.55 }, "coding": { "sweVerifiedArcee": 63.2, "aaCodingIndex": 27.19, "terminalBenchHard": 22.7, "aaSciCode": 36.1 }, "reasoning": { "lcr": 33, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1181 }, "knowledge": { "gpqaDiamond": 76.3, "mmluProArcee": 83.4, "artificialAnalysis": 31.87, "aaGpqaDiamond": 75.2, "aaHle": 14.7, "aaOmniscienceIndex": -44.2, "omniscienceAccuracy": 22.8, "omniscienceHallucinationRate": 86.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 56.3 }, "math": { "aime2025Arcee": 96.3 } } }, { "slug": "qwen3-max", "canonicalModelKey": "qwen3-max", "model": "Qwen3 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 12, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-max.md", "id": 233, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-max", "familyName": "Qwen3 Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-max", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 12, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 43.01, "tau2Bench": 74.3, "gdpvalAaNormalized": 26.8, "gdpvalAa": 1037, "gertLabs": 43.74 }, "coding": { "vibeCodeBench": 3.506, "aaCodingIndex": 26.41, "terminalBenchHard": 20.5, "aaSciCode": 38.3 }, "reasoning": { "lcr": 46.7, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1164 }, "knowledge": { "artificialAnalysis": 31.38, "aaGpqaDiamond": 76.4, "aaHle": 11.1, "aaOmniscienceIndex": -43.1, "omniscienceAccuracy": 24.4, "omniscienceHallucinationRate": 89.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.1 }, "math": {} } }, { "slug": "glm-4-7-flash", "canonicalModelKey": "glm-4-7-flash", "model": "GLM-4.7-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 11, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-4-7-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7-flash.md", "id": 186, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-7-flash", "familyName": "GLM-4.7-Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-7-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 11, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 50, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mercury-2", "canonicalModelKey": "mercury-2", "model": "Mercury 2", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 11, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md", "id": 184, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "mercury-2", "familyName": "Mercury 2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mercury-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 11, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 48, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-350m", "canonicalModelKey": "lfm2-5-350m", "model": "LFM2.5-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 11, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-350m.md", "id": 159, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-350m", "familyName": "LFM2.5-350M", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-350m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 11, "overallScore": 11, "rawOverallScore": 11, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 0.5, "multilingual": null, "instructionFollowing": 36.5, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 105 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "nemotron-3-super-120b-a12b", "canonicalModelKey": "nemotron-3-super-120b-a12b", "model": "Nemotron 3 Super 120B A12B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 10, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/nemotron-3-super-120b-a12b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-120b-a12b.md", "id": 187, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-super-120b-a12b", "familyName": "Nemotron 3 Super 120B A12B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-super-120b-a12b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 10, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 50, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "granite-4-0-h-1b", "canonicalModelKey": "granite-4-0-h-1b", "model": "Granite-4.0-H-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 9, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-h-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-1b.md", "id": 152, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-1b", "familyName": "Granite 4.0 1B", "variantType": "hybrid", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-h-1b", "relatedModelKeys": [ "granite-4-0-1b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 9, "overallScore": 11, "rawOverallScore": 11, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 0.1, "multilingual": null, "instructionFollowing": 38, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multilingual": 104, "instructionFollowing": 99 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 6.53, "tau2Bench": 19.6, "gdpvalAaNormalized": 0, "gdpvalAa": 268 }, "coding": { "aaCodingIndex": 2.74, "terminalBenchHard": 0, "aaSciCode": 8.2 }, "reasoning": { "lcr": 6.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 7.99, "aaGpqaDiamond": 26.3, "aaHle": 5, "aaOmniscienceIndex": -73.6, "omniscienceAccuracy": 5.3, "omniscienceHallucinationRate": 83.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 26.2 }, "math": {} } }, { "slug": "seed-1-6", "canonicalModelKey": "seed-1-6", "model": "Seed 1.6", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 7, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/seed-1-6", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6.md", "id": 183, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "seed-1-6", "familyName": "Seed 1.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "seed-1-6", "relatedModelKeys": [ "seed-1-6-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 7, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen2-5-coder-32b-instruct", "canonicalModelKey": "qwen2-5-coder-32b-instruct", "model": "Qwen2.5 Coder 32B Instruct", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 6, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen2-5-coder-32b-instruct", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-coder-32b-instruct.md", "id": 216, "releaseDate": "2025-01-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-coder", "familyName": "Qwen2.5 Coder", "variantType": "32b-instruct", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-coder-32b-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 6, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 27.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 12.87, "aaGpqaDiamond": 41.7, "aaHle": 3.8 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "seed-2-0-lite", "canonicalModelKey": "seed-2-0-lite", "model": "Seed-2.0-Lite", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 6, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/seed-2-0-lite", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-lite.md", "id": 185, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "seed-2-0", "familyName": "Seed 2.0", "variantType": "lite", "snapshotLabel": null, "baseFamilyModelKey": "seed-2-0-lite", "relatedModelKeys": [ "seed-2-0-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 6, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepseek-r1-distill-qwen-32b", "canonicalModelKey": "deepseek-r1-distill-qwen-32b", "model": "DeepSeek R1 Distill Qwen 32B", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 6, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepseek-r1-distill-qwen-32b", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1-distill-qwen-32b.md", "id": 217, "releaseDate": "2025-01-20", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-r1-distill", "familyName": "DeepSeek R1 Distill", "variantType": "qwen-32b", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-r1-distill-qwen-32b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 6, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 37.6 }, "reasoning": { "lcr": 9.7 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 17.17, "aaGpqaDiamond": 61.5, "aaHle": 5.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 22.9 }, "math": {} } }, { "slug": "ministral-3-14b-reasoning", "canonicalModelKey": "ministral-3-14b-reasoning", "model": "Ministral 3 14B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 5, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-14b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b-reasoning.md", "id": 188, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-14b", "familyName": "Ministral 3 14B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-14b", "relatedModelKeys": [ "ministral-3-14b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 5, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ministral-3-14b", "canonicalModelKey": "ministral-3-14b", "model": "Ministral 3 14B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 5, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-14b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b.md", "id": 192, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-14b", "familyName": "Ministral 3 14B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-14b", "relatedModelKeys": [ "ministral-3-14b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 5, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "aion-2-0", "canonicalModelKey": "aion-2-0", "model": "Aion-2.0", "creator": "Aion Labs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 5, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/aion-2-0", "markdownUrl": "https://benchlm.ai/md/models/aion-2-0.md", "id": 190, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "aion-2-0", "familyName": "Aion-2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "aion-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 5, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "seed-1-6-flash", "canonicalModelKey": "seed-1-6-flash", "model": "Seed 1.6 Flash", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 4, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/seed-1-6-flash", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6-flash.md", "id": 191, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "seed-1-6", "familyName": "Seed 1.6", "variantType": "flash", "snapshotLabel": null, "baseFamilyModelKey": "seed-1-6", "relatedModelKeys": [ "seed-1-6" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 4, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "minimax-m1-80k", "canonicalModelKey": "minimax-m1-80k", "model": "MiniMax M1 80k", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "80K", "contextWindowTokens": 80000, "displayScore": 4, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/minimax-m1-80k", "markdownUrl": "https://benchlm.ai/md/models/minimax-m1-80k.md", "id": 195, "releaseDate": "2025-01-15", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m1-80k", "familyName": "MiniMax M1 80k", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m1-80k", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 4, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 48, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "solar-pro-2", "canonicalModelKey": "solar-pro-2", "model": "Solar Pro 2", "creator": "Upstage", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 4, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/solar-pro-2", "markdownUrl": "https://benchlm.ai/md/models/solar-pro-2.md", "id": 208, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "solar", "familyName": "Solar", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "solar-pro-2", "relatedModelKeys": [ "solar-wbl" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 4, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 12.71, "tau2Bench": 31.9, "gdpvalAaNormalized": 0, "gdpvalAa": 443 }, "coding": { "aaCodingIndex": 11.29, "terminalBenchHard": 4.5, "aaSciCode": 24.8 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 13.59, "aaGpqaDiamond": 56.1, "aaHle": 3.8, "aaOmniscienceIndex": -61.7, "omniscienceAccuracy": 15.6, "omniscienceHallucinationRate": 91.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.7 }, "math": {}, "korean": {} } }, { "slug": "seed-2-0-mini", "canonicalModelKey": "seed-2-0-mini", "model": "Seed-2.0-Mini", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 3, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/seed-2-0-mini", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-mini.md", "id": 193, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "seed-2-0", "familyName": "Seed 2.0", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "seed-2-0-lite", "relatedModelKeys": [ "seed-2-0-lite" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 3, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 32, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ministral-3-8b-reasoning", "canonicalModelKey": "ministral-3-8b-reasoning", "model": "Ministral 3 8B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 3, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-8b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b-reasoning.md", "id": 197, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-8b", "familyName": "Ministral 3 8B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-8b", "relatedModelKeys": [ "ministral-3-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 3, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ministral-3-8b", "canonicalModelKey": "ministral-3-8b", "model": "Ministral 3 8B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 3, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-8b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b.md", "id": 199, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-8b", "familyName": "Ministral 3 8B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-8b", "relatedModelKeys": [ "ministral-3-8b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 3, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-24b-a2b", "canonicalModelKey": "lfm2-24b-a2b", "model": "LFM2-24B-A2B", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 2, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-24b-a2b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-24b-a2b.md", "id": 196, "releaseDate": "2026-01-10", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-24b-a2b", "familyName": "LFM2-24B-A2B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-24b-a2b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 2, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 48, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-1-2b-thinking", "canonicalModelKey": "lfm2-5-1-2b-thinking", "model": "LFM2.5-1.2B-Thinking", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 1, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-thinking", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-thinking.md", "id": 198, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5 1.2B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-instruct" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 1, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 48, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ministral-3-3b-reasoning", "canonicalModelKey": "ministral-3-3b-reasoning", "model": "Ministral 3 3B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 1, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-3b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b-reasoning.md", "id": 200, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-3b", "familyName": "Ministral 3 3B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-3b", "relatedModelKeys": [ "ministral-3-3b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 1, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ministral-3-3b", "canonicalModelKey": "ministral-3-3b", "model": "Ministral 3 3B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 1, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ministral-3-3b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b.md", "id": 202, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-3b", "familyName": "Ministral 3 3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-3b", "relatedModelKeys": [ "ministral-3-3b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 1, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 49, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "exaone-4-0-1-2b", "canonicalModelKey": "exaone-4-0-1-2b", "model": "Exaone 4.0 1.2B", "creator": "LG AI Research", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 1, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/exaone-4-0-1-2b", "markdownUrl": "https://benchlm.ai/md/models/exaone-4-0-1-2b.md", "id": 205, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-4", "familyName": "Exaone 4.0", "variantType": "1-2b", "snapshotLabel": null, "baseFamilyModelKey": "exaone-4-0-32b", "relatedModelKeys": [ "exaone-4-0-32b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 1, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 6.82, "tau2Bench": 20.5, "gdpvalAaNormalized": 0, "gdpvalAa": 293 }, "coding": { "aaCodingIndex": 2.47, "terminalBenchHard": 0, "aaSciCode": 7.4 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 8.11, "aaGpqaDiamond": 42.4, "aaHle": 5.8, "aaOmniscienceIndex": -82.6, "omniscienceAccuracy": 4.7, "omniscienceHallucinationRate": 91.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 25.3 }, "math": {}, "korean": {} } }, { "slug": "step-3-5-flash", "canonicalModelKey": "step-3-5-flash", "model": "Step 3.5 Flash", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/step-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-5-flash.md", "id": 181, "releaseDate": "2026-01-20", "market": null, "isRegional": false, "family": { "familyKey": "step-3-5-flash", "familyName": "Step 3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-3-5-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 55, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "minimax-m2-5", "canonicalModelKey": "minimax-m2-5", "model": "MiniMax M2.5", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/minimax-m2-5", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-5.md", "id": 189, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m2-5", "familyName": "MiniMax M2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m2-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 52, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 14.852 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-mini", "canonicalModelKey": "gpt-5-mini", "model": "GPT-5 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-mini.md", "id": 182, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-medium", "gpt-5-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 59, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 14.171 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "lfm2-5-1-2b-instruct", "canonicalModelKey": "lfm2-5-1-2b-instruct", "model": "LFM2.5-1.2B-Instruct", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-instruct", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-instruct.md", "id": 201, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5 1.2B", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 48, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-vl-450m", "canonicalModelKey": "lfm2-5-vl-450m", "model": "LFM2.5-VL-450M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m.md", "id": 168, "releaseDate": "2026-04-08", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-450m", "familyName": "LFM2.5-VL-450M", "variantType": "vl", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-450m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": 33, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 21.6, "multilingual": null, "instructionFollowing": 61.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 130 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 21.08 }, "coding": {}, "reasoning": {}, "multimodalGrounded": { "mmmu": 32.67, "realWorldQa": 58.43, "countBench": 73.31 }, "knowledge": { "gpqa": 25.66, "mmluPro": 19.32 }, "multilingual": {}, "instructionFollowing": { "ifeval": 61.16 }, "math": {} } }, { "slug": "lfm2-5-vl-1-6b-extract", "canonicalModelKey": "lfm2-5-vl-1-6b-extract", "model": "LFM2.5-VL-1.6B-Extract", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-1-6b-extract", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-1-6b-extract.md", "id": 256, "releaseDate": "2026-05-26", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-extract", "familyName": "LFM2.5-VL Extract", "variantType": "1-6b", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-1-6b-extract", "relatedModelKeys": [ "lfm2-5-vl-450m-extract", "lfm2-5-vl-450m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 2.83, "tau2Bench": 8.5, "gdpvalAaNormalized": 0, "gdpvalAa": 232 }, "coding": { "aaCodingIndex": 1, "terminalBenchHard": 0, "aaSciCode": 3 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": { "liquidExtractJsonValidity": 99.6, "liquidExtractSchemaF1": 99.6, "liquidExtractVlmJudge": 90.6, "aaMmmuPro": 26.5 }, "knowledge": { "artificialAnalysis": 6.18, "aaGpqaDiamond": 28.9, "aaHle": 5.1, "aaOmniscienceIndex": -83.9, "omniscienceAccuracy": 5.2, "omniscienceHallucinationRate": 94 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.1 }, "math": {} } }, { "slug": "lfm2-5-vl-450m-extract", "canonicalModelKey": "lfm2-5-vl-450m-extract", "model": "LFM2.5-VL-450M-Extract", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m-extract", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m-extract.md", "id": 255, "releaseDate": "2026-05-26", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-extract", "familyName": "LFM2.5-VL Extract", "variantType": "450m", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-1-6b-extract", "relatedModelKeys": [ "lfm2-5-vl-1-6b-extract", "lfm2-5-vl-450m" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "liquidExtractJsonValidity": 98.9, "liquidExtractSchemaF1": 98.8, "liquidExtractVlmJudge": 84.5 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md", "id": 258, "releaseDate": "2026-06-12", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-7-code", "familyName": "Kimi K2.7 Code", "variantType": "code", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-7-code", "relatedModelKeys": [ "kimi-2-6", "kimi-k2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "kimi-2-6" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "kimiClaw247": 46.9, "mcpAtlas": 76, "mcpMarkVerified": 81.1 }, "coding": { "kimiCodeBenchV2": 62, "programBench": 53.6, "mlsBenchLite": 35.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b", "canonicalModelKey": "holo3-1-35b-a3b", "model": "Holo3.1-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b.md", "id": 242, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "holo3-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 79.3 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-4b", "canonicalModelKey": "holo3-1-4b", "model": "Holo3.1-4B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-4b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-4b.md", "id": 247, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-4b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 71 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-9b", "canonicalModelKey": "holo3-1-9b", "model": "Holo3.1-9B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-9b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-9b.md", "id": 246, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "9b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-8b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 71 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "composer-2-fast", "canonicalModelKey": "composer-2-fast", "model": "Composer 2 Fast", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-fast", "markdownUrl": "https://benchlm.ai/md/models/composer-2-fast.md", "id": 176, "releaseDate": "2026-03-19", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "fast", "snapshotLabel": null, "baseFamilyModelKey": "composer-2", "relatedModelKeys": [ "composer-2" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "reactNativeEvals": 94.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen3-5-plus", "canonicalModelKey": "qwen3-5-plus", "model": "Qwen3.5 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-5-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-plus.md", "id": 227, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-plus", "familyName": "Qwen3.5 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-plus", "relatedModelKeys": [ "qwen3-5-397b", "qwen3-5-397b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 15.738 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-haiku-4-5-thinking", "canonicalModelKey": "claude-haiku-4-5-thinking", "model": "Claude Haiku 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-haiku-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5-thinking.md", "id": 232, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "claude-haiku-4-5", "familyName": "Claude Haiku 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-haiku-4-5", "relatedModelKeys": [ "claude-haiku-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 11.393 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1167 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-sonnet-4-5-thinking", "canonicalModelKey": "claude-sonnet-4-5-thinking", "model": "Claude Sonnet 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-sonnet-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5-thinking.md", "id": 229, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-5", "familyName": "Claude Sonnet 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-sonnet-4-5", "relatedModelKeys": [ "claude-sonnet-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 22.621 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1235 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-235b-a22b", "canonicalModelKey": "holo2-235b-a22b", "model": "Holo2-235B-A22B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-235b-a22b", "markdownUrl": "https://benchlm.ai/md/models/holo2-235b-a22b.md", "id": 223, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "235b-a22b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-30b-a3b", "holo2-8b", "holo2-4b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 70.6 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-30b-a3b", "canonicalModelKey": "holo2-30b-a3b", "model": "Holo2-30B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo2-30b-a3b.md", "id": 224, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "30b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-8b", "holo2-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 66.1 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-4b", "canonicalModelKey": "holo2-4b", "model": "Holo2-4B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-4b", "markdownUrl": "https://benchlm.ai/md/models/holo2-4b.md", "id": 226, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-30b-a3b", "holo2-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 57.2 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-8b", "canonicalModelKey": "holo2-8b", "model": "Holo2-8B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-8b", "markdownUrl": "https://benchlm.ai/md/models/holo2-8b.md", "id": 225, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-30b-a3b", "holo2-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 58.9 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-0-8b", "canonicalModelKey": "holo3-1-0-8b", "model": "Holo3.1-0.8B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-0-8b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-0-8b.md", "id": 248, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "0-8b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-fp8", "canonicalModelKey": "holo3-1-35b-a3b-fp8", "model": "Holo3.1-35B-A3B-FP8", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-fp8", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-fp8.md", "id": 243, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-fp8", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-gguf", "canonicalModelKey": "holo3-1-35b-a3b-gguf", "model": "Holo3.1-35B-A3B-GGUF", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-gguf", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-gguf.md", "id": 245, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-gguf", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-nvfp4", "canonicalModelKey": "holo3-1-35b-a3b-nvfp4", "model": "Holo3.1-35B-A3B-NVFP4", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-nvfp4.md", "id": 244, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-nvfp4", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-1-2b-jp-202606", "canonicalModelKey": "lfm2-5-1-2b-jp-202606", "model": "LFM2.5-1.2B-JP-202606", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-jp-202606", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-jp-202606.md", "id": 254, "releaseDate": "2026-05-26", "market": "Japan", "isRegional": true, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5-1.2B", "variantType": "jp-202606", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-instruct", "lfm2-5-1-2b-thinking" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-build-0-1", "canonicalModelKey": "grok-build-0-1", "model": "Grok Build 0.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-build-0-1", "markdownUrl": "https://benchlm.ai/md/models/grok-build-0-1.md", "id": 173, "releaseDate": "2026-05-20", "market": null, "isRegional": false, "family": { "familyKey": "grok-build", "familyName": "Grok Build", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-build-0-1", "relatedModelKeys": [ "grok-code-fast-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "gertLabs": 49.15 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hy-mt1-5-1-8b-1-25bit", "canonicalModelKey": "hy-mt1-5-1-8b-1-25bit", "model": "Hy-MT1.5-1.8B-1.25bit", "creator": "Tencent Hunyuan", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hy-mt1-5-1-8b-1-25bit", "markdownUrl": "https://benchlm.ai/md/models/hy-mt1-5-1-8b-1-25bit.md", "id": 237, "releaseDate": "2026-04-29", "market": null, "isRegional": false, "family": { "familyKey": "hy-mt1-5-1-8b", "familyName": "Hy-MT1.5-1.8B", "variantType": "1.25bit", "snapshotLabel": null, "baseFamilyModelKey": "hy-mt1-5-1-8b-1-25bit", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "leanstral", "canonicalModelKey": "leanstral", "model": "Leanstral", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/leanstral", "markdownUrl": "https://benchlm.ai/md/models/leanstral.md", "id": 203, "releaseDate": "2026-03-15", "market": null, "isRegional": false, "family": { "familyKey": "leanstral", "familyName": "Leanstral", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "leanstral", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "granite-4-0-350m", "canonicalModelKey": "granite-4-0-350m", "model": "Granite-4.0-350M", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-350m.md", "id": 171, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-350m", "familyName": "Granite 4.0 350M", "variantType": "dense", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-350m", "relatedModelKeys": [ "granite-4-0-h-350m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multilingual": 105, "instructionFollowing": 131 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 4.39, "tau2Bench": 13.2, "gdpvalAaNormalized": 0, "gdpvalAa": 268 }, "coding": { "aaCodingIndex": 0.31, "terminalBenchHard": 0, "aaSciCode": 0.9 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 6.1, "aaGpqaDiamond": 26.1, "aaHle": 5.7, "aaOmniscienceIndex": -72.1, "omniscienceAccuracy": 3.2, "omniscienceHallucinationRate": 77.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 15.9 }, "math": {} } }, { "slug": "granite-4-0-h-350m", "canonicalModelKey": "granite-4-0-h-350m", "model": "Granite-4.0-H-350M", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-h-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-350m.md", "id": 172, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-350m", "familyName": "Granite 4.0 350M", "variantType": "hybrid", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-350m", "relatedModelKeys": [ "granite-4-0-350m" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "multilingual": 106, "instructionFollowing": 132 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 4.87, "tau2Bench": 14.6, "gdpvalAaNormalized": 0, "gdpvalAa": 289 }, "coding": { "aaCodingIndex": 0.58, "terminalBenchHard": 0, "aaSciCode": 1.7 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 5.44, "aaGpqaDiamond": 25.7, "aaHle": 6.4, "aaOmniscienceIndex": -87.2, "omniscienceAccuracy": 3.7, "omniscienceHallucinationRate": 94.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 17.6 }, "math": {} } }, { "slug": "gpt-5-nano", "canonicalModelKey": "gpt-5-nano", "model": "GPT-5 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-nano.md", "id": 194, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-medium", "gpt-5-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 31, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "skt-ax", "canonicalModelKey": "skt-ax", "model": "A.X series", "creator": "SK Telecom", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/skt-ax", "markdownUrl": "https://benchlm.ai/md/models/skt-ax.md", "id": 212, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "skt-ax", "familyName": "A.X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "skt-ax", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "dna-1-0", "canonicalModelKey": "dna-1-0", "model": "DNA 1.0 8B", "creator": "Community", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/dna-1-0", "markdownUrl": "https://benchlm.ai/md/models/dna-1-0.md", "id": 215, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "dna-1-0", "familyName": "DNA 1.0", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "dna-1-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "holotron-12b", "canonicalModelKey": "holotron-12b", "model": "Holotron-12B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holotron-12b", "markdownUrl": "https://benchlm.ai/md/models/holotron-12b.md", "id": 222, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holotron", "familyName": "Holotron", "variantType": "12b", "snapshotLabel": null, "baseFamilyModelKey": "holotron-12b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hyperclova-x-dash", "canonicalModelKey": "hyperclova-x-dash", "model": "HyperClova X Dash", "creator": "Naver Cloud", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hyperclova-x-dash", "markdownUrl": "https://benchlm.ai/md/models/hyperclova-x-dash.md", "id": 207, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "hyperclova", "familyName": "HyperClova X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "hyperclova-x-think", "relatedModelKeys": [ "hyperclova-x-think", "hyperclova-x-seed-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "hyperclova-x-think", "canonicalModelKey": "hyperclova-x-think", "model": "HyperClova X Think 32B", "creator": "Naver Cloud", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hyperclova-x-think", "markdownUrl": "https://benchlm.ai/md/models/hyperclova-x-think.md", "id": 206, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "hyperclova", "familyName": "HyperClova X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "hyperclova-x-think", "relatedModelKeys": [ "hyperclova-x-dash", "hyperclova-x-seed-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kanana-essence", "canonicalModelKey": "kanana-essence", "model": "Kanana Essence", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-essence", "markdownUrl": "https://benchlm.ai/md/models/kanana-essence.md", "id": 210, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-flag", "kanana-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kanana-flag", "canonicalModelKey": "kanana-flag", "model": "Kanana Flag", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-flag", "markdownUrl": "https://benchlm.ai/md/models/kanana-flag.md", "id": 209, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-essence", "kanana-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kanana-nano", "canonicalModelKey": "kanana-nano", "model": "Kanana Nano", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-nano", "markdownUrl": "https://benchlm.ai/md/models/kanana-nano.md", "id": 211, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-flag", "kanana-essence" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "orion-mistral-24b", "canonicalModelKey": "orion-mistral-24b", "model": "OriOn-Mistral-24B", "creator": "LightOn", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "344K", "contextWindowTokens": 344000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/orion-mistral-24b", "markdownUrl": "https://benchlm.ai/md/models/orion-mistral-24b.md", "id": 221, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "orion", "familyName": "OriOn", "variantType": "mistral-24b", "snapshotLabel": null, "baseFamilyModelKey": "orion-qwen-32b", "relatedModelKeys": [ "orion-qwen-32b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "orion-qwen-32b", "canonicalModelKey": "orion-qwen-32b", "model": "OriOn-Qwen-32B", "creator": "LightOn", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/orion-qwen-32b", "markdownUrl": "https://benchlm.ai/md/models/orion-qwen-32b.md", "id": 220, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "orion", "familyName": "OriOn", "variantType": "qwen-32b", "snapshotLabel": null, "baseFamilyModelKey": "orion-qwen-32b", "relatedModelKeys": [ "orion-mistral-24b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "pharia-1-llm-7b-control", "canonicalModelKey": "pharia-1-llm-7b-control", "model": "Pharia-1-LLM-7B-control", "creator": "Aleph Alpha", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pharia-1-llm-7b-control", "markdownUrl": "https://benchlm.ai/md/models/pharia-1-llm-7b-control.md", "id": 218, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "pharia-1-llm-7b", "familyName": "Pharia-1-LLM-7B", "variantType": "control", "snapshotLabel": null, "baseFamilyModelKey": "pharia-1-llm-7b-control", "relatedModelKeys": [ "pharia-1-llm-7b-control-aligned" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "pharia-1-llm-7b-control-aligned", "canonicalModelKey": "pharia-1-llm-7b-control-aligned", "model": "Pharia-1-LLM-7B-control-aligned", "creator": "Aleph Alpha", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pharia-1-llm-7b-control-aligned", "markdownUrl": "https://benchlm.ai/md/models/pharia-1-llm-7b-control-aligned.md", "id": 219, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "pharia-1-llm-7b", "familyName": "Pharia-1-LLM-7B", "variantType": "control-aligned", "snapshotLabel": null, "baseFamilyModelKey": "pharia-1-llm-7b-control", "relatedModelKeys": [ "pharia-1-llm-7b-control" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "thunder-llm", "canonicalModelKey": "thunder-llm", "model": "Thunder-LLM 8B", "creator": "Academic", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/thunder-llm", "markdownUrl": "https://benchlm.ai/md/models/thunder-llm.md", "id": 214, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "thunder-llm", "familyName": "Thunder-LLM", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "thunder-llm", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "varco", "canonicalModelKey": "varco", "model": "Varco", "creator": "NC AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 0, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/varco", "markdownUrl": "https://benchlm.ai/md/models/varco.md", "id": 213, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "varco", "familyName": "Varco", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "varco", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } } ] }