{ "schemaVersion": "1.0", "name": "BenchLM leaderboards", "description": "Overall and category leaderboards derived from the public BenchLM ranking logic.", "canonicalUrl": "https://benchlm.ai/data/leaderboard.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", "src/data/scoring.js" ], "counts": { "overall": 123, "categories": { "agentic": 102, "coding": 101, "reasoning": 93, "multimodalGrounded": 110, "knowledge": 107, "multilingual": 106, "instructionFollowing": 132, "math": 87 } }, "items": [ { "rank": 1, "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", "score": 99, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 97, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 93, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 4, "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", "score": 91, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 5, "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", "score": 91, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 33, "scoreConfidence": 3 }, { "rank": 6, "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", "score": 90, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 7, "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", "score": 89, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 8, "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", "score": 89, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 9, "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", "score": 89, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 10, "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", "score": 88, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 11, "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", "score": 88, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 12, "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", "score": 86, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 13, "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", "score": 86, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 14, "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", "score": 86, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 15, "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", "score": 85, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 16, "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", "score": 84, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 17, "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", "score": 82, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 18, "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", "score": 82, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 19, "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", "score": 82, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 20, "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", "score": 82, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 81, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 28, "scoreConfidence": 2 }, { "rank": 22, "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", "score": 80, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 23, "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", "score": 79, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 24, "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", "score": 79, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 78, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 26, "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", "score": 77, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 27, "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", "score": 77, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 76, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 29, "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", "score": 76, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 76, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 75, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 32, "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", "score": 75, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 74, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 34, "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", "score": 72, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 37, "scoreConfidence": 2 }, { "rank": 35, "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", "score": 71, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 36, "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", "score": 71, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 37, "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", "score": 70, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 38, "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", "score": 68, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 39, "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", "score": 68, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 40, "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", "score": 68, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 68, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 67, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 43, "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", "score": 66, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 44, "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", "score": 65, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 45, "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", "score": 65, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 40, "scoreConfidence": 2 }, { "rank": 46, "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", "score": 64, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 63, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 48, "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", "score": 63, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 49, "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", "score": 63, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 63, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 62, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 52, "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", "score": 61, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 53, "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", "score": 60, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 59, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 57, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 56, "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", "score": 57, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 57, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 57, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 56, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 56, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 56, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 55, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 63, "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", "score": 55, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 55, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 53, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 66, "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", "score": 51, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 51, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 50, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 50, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 50, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 49, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 49, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 49, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 48, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 47, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 45, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 45, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 43, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 43, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 43, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 42, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 41, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 40, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 40, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 39, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 39, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 38, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 37, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 35, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 34, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 34, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 34, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 34, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 32, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 32, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 32, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 30, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 29, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 28, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 27, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 27, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 25, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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", "score": 25, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "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", "score": 25, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 25, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 24, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 107, "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", "score": 24, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 108, "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", "score": 24, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 109, "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", "score": 23, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 110, "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", "score": 23, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 111, "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", "score": 23, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 112, "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", "score": 22, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 113, "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", "score": 22, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 114, "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", "score": 22, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 115, "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", "score": 22, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 116, "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", "score": 18, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 117, "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", "score": 17, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 118, "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", "score": 16, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 119, "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", "score": 16, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 120, "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", "score": 11, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 121, "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", "score": 10, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 122, "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", "score": 4, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 123, "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", "score": 1, "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "categories": { "agentic": [ { "rank": 1, "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", "score": 100, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 100, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 96.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 4, "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", "score": 95.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 5, "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", "score": 95.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 6, "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", "score": 93.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 89.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 8, "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", "score": 87.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 9, "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", "score": 86.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 10, "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", "score": 85.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 11, "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", "score": 84.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 12, "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", "score": 82.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 28, "scoreConfidence": 2 }, { "rank": 13, "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", "score": 81.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 14, "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", "score": 81.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 15, "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", "score": 78.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 16, "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", "score": 77.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 77, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 18, "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", "score": 76.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 19, "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", "score": 74.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 74.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 73.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 22, "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", "score": 70.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 23, "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", "score": 68.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 68.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 62, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 26, "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", "score": 61.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 27, "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", "score": 61.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 61.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 29, "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", "score": 61.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 59.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 59.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 32, "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", "score": 57.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 57.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 56.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 56.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 55.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 37, "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", "score": 55.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 38, "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", "score": 55.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 39, "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", "score": 54.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 54, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 53.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 53.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 43, "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", "score": 53.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 44, "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", "score": 53.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 50.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 46, "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", "score": 50, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 49.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 48.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 49, "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", "score": 46.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 45, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 51, "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", "score": 44.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 52, "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", "score": 44.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 44.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 43.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 43.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 43.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 41.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 40.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 39, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 38.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 38.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 38.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 38.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 38.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 37.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 34.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 33.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 33.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 33, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 32.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 32.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 31.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 31.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 25.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 24.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 23.1, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 22.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 22.9, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 22, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 21.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 21, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 19.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 19.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 18.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 18.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 18.3, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 17.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 17.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 17.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 17.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 16.4, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 16.2, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 14.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 12.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 12.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 11.7, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 8.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 8.5, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 7.6, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 4.8, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 0, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 0, "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "coding": [ { "rank": 1, "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", "score": 100, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 100, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 98, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 4, "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", "score": 93.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 5, "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", "score": 93, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 6, "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", "score": 91.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 33, "scoreConfidence": 3 }, { "rank": 7, "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", "score": 89.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 28, "scoreConfidence": 2 }, { "rank": 8, "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", "score": 89.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 9, "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", "score": 87.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 10, "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", "score": 87.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 11, "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", "score": 87.1, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 12, "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", "score": 86, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 13, "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", "score": 85.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 14, "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", "score": 85, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 15, "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", "score": 84.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 16, "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", "score": 82.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 17, "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", "score": 82.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 18, "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", "score": 82.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 19, "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", "score": 82, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 20, "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", "score": 81.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 81, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 22, "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", "score": 80.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 23, "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", "score": 78.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 78.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 25, "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", "score": 78.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 26, "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", "score": 77.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 37, "scoreConfidence": 2 }, { "rank": 27, "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", "score": 77.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 77.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 29, "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", "score": 77.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 77.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 31, "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", "score": 76.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 32, "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", "score": 76, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 76, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 75.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 35, "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", "score": 73.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 72.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 37, "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", "score": 72.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 38, "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", "score": 72.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 40, "scoreConfidence": 2 }, { "rank": 39, "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", "score": 70.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 40, "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", "score": 69.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 69.1, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 68.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 68.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 44, "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", "score": 67.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 45, "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", "score": 65.1, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 62, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 47, "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", "score": 61.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 60.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 59.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 59.1, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 51, "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", "score": 57.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 56.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 54.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 54, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 55, "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", "score": 53.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 53.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 51.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 51.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 51.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 48.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 48.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 47.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 46.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 45.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 45.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 43, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 41.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 40.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 37.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 36.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 32.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 28.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 26.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 26.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 25.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 24.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 22.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 21.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 21.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 21.2, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 21, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 20.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 18.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 16.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 16.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 15.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 14.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 13.4, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 12.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 12.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 9.3, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 8.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 7.8, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 7.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 5.5, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 3.9, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 2.6, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 1, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 0.7, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 0, "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "reasoning": [ { "rank": 1, "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", "score": 97.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 2, "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", "score": 96.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 95.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 4, "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", "score": 93, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 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", "score": 88.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 6, "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", "score": 88.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 88.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 8, "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", "score": 88.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 9, "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", "score": 87.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 10, "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", "score": 87.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 11, "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", "score": 87.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 12, "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", "score": 83.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 13, "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", "score": 82.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 14, "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", "score": 82.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 15, "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", "score": 81.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 16, "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", "score": 80.3, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 79.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 18, "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", "score": 76.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 19, "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", "score": 76.3, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 75, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 74.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 22, "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", "score": 72.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 23, "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", "score": 70.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 70.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 69.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 26, "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", "score": 69.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 27, "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", "score": 68, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 67.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 29, "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", "score": 66.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 66.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 64.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 32, "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", "score": 62, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 60.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 34, "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", "score": 60.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 60.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 59.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 37, "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", "score": 59, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 38, "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", "score": 58.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 39, "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", "score": 58.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 58.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 41, "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", "score": 58.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 57, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 55.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 44, "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", "score": 55.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 55.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 55.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 55, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 54.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 54.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 50, "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", "score": 52.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 52, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 50.3, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 49.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 49.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 48.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 47.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 46.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 44.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 44, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 43.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 43, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 41.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 39.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 38.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 37.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 35.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 33.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 32.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 32.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 30.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 30.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 29.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 28.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 28.1, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 27.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 26.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 26.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 25.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 24.4, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 23.5, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 20.6, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 19.9, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 19.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 18, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 15.3, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 14.8, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 14.2, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 11.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 2.7, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 0, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 0, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 0, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 0, "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "multimodalGrounded": [ { "rank": 1, "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", "score": 100, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 2, "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", "score": 98.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 97.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 4, "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", "score": 96.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 5, "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", "score": 95.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 6, "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", "score": 94.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 93.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 8, "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", "score": 90.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 9, "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", "score": 90.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 10, "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", "score": 89.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 11, "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", "score": 89, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 12, "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", "score": 86.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 13, "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", "score": 85.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 14, "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", "score": 84, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 15, "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", "score": 81.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 16, "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", "score": 81.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 17, "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", "score": 80, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 18, "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", "score": 79, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 19, "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", "score": 78.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 20, "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", "score": 77.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 76.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 22, "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", "score": 76, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 23, "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", "score": 75.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 73.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 73, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 26, "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", "score": 72.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 27, "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", "score": 72, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 71.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 29, "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", "score": 71.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 28, "scoreConfidence": 2 }, { "rank": 30, "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", "score": 70, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 31, "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", "score": 68.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 32, "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", "score": 67.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 33, "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", "score": 67.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 67.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 66.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 66.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 37, "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", "score": 65.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 38, "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", "score": 65.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 39, "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", "score": 65.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 65.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 41, "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", "score": 65.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 42, "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", "score": 65.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 43, "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", "score": 65, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 37, "scoreConfidence": 2 }, { "rank": 44, "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", "score": 64.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 64, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 40, "scoreConfidence": 2 }, { "rank": 46, "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", "score": 63.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 63.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 48, "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", "score": 63.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 49, "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", "score": 62.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 61.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 61.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 52, "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", "score": 59.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 53, "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", "score": 59, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 58.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 58.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 58.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 58.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 58.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 58, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 60, "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", "score": 56.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 56, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 62, "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", "score": 55.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 55.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 54.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 54, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 53.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 51.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 50.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 50, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 48.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 71, "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", "score": 47.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 72, "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", "score": 47.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 45, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 74, "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", "score": 43.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 41.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 41.1, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 40, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 37.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 36.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 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", "score": 36.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 34.6, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 32.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 31.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 31.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 26.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 25.8, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 22.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 21.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 20.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 19.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 18.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 18.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 18.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 17, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 12.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 11.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 9.4, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 7.3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 6.9, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 6.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 6.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 5.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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", "score": 5.2, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "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", "score": 3.7, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 3, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 1.5, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 107, "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", "score": 0, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 108, "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", "score": 0, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 109, "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", "score": 0, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 110, "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", "score": 0, "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "knowledge": [ { "rank": 1, "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", "score": 99.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 98.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 3, "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", "score": 98.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 4, "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", "score": 93.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 5, "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", "score": 93.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 6, "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", "score": 92, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 91.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 8, "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", "score": 90.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 9, "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", "score": 86.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 10, "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", "score": 85.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 33, "scoreConfidence": 3 }, { "rank": 11, "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", "score": 83.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 12, "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", "score": 83, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 13, "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", "score": 82.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 14, "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", "score": 82.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 15, "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", "score": 81.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 16, "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", "score": 81.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 81.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 18, "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", "score": 80.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 19, "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", "score": 79.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 79.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 21, "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", "score": 78.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 22, "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", "score": 78.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 23, "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", "score": 78, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 78, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 25, "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", "score": 77.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 26, "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", "score": 76.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 27, "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", "score": 75.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 28, "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", "score": 75.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 29, "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", "score": 75.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 74, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 31, "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", "score": 73.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 32, "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", "score": 73.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 73.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 72.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 71.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 36, "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", "score": 70.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 37, "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", "score": 70.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 38, "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", "score": 68.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 37, "scoreConfidence": 2 }, { "rank": 39, "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", "score": 66.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 40, "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", "score": 66.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 66.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 66.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 65.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 40, "scoreConfidence": 2 }, { "rank": 44, "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", "score": 65.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 65.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 64.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 64.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 48, "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", "score": 63.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 62.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 62.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 51, "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", "score": 59.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 58, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 57.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 56.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 56.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 56, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 55.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 53.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 51.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 50.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 61, "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", "score": 50.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 49.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 63, "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", "score": 48.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 48.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 47.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 46.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 45.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 44.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 21, "scoreConfidence": 2 }, { "rank": 69, "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", "score": 44.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 44, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 43.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 42.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 41.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 40, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 39.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 38.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 35.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 35.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 35.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 35.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 35.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 34.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 34.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 31.5, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 30.1, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 86, "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", "score": 29.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 28.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 26.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 26, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 25.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 25.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 25.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 25.2, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 25, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 24.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 16.6, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 15.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 14.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 13.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 13.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 11.7, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 10.3, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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", "score": 9.8, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "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", "score": 8.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 5.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 4.9, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 107, "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", "score": 2.4, "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "multilingual": [ { "rank": 1, "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", "score": 100, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 100, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 3, "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", "score": 100, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 4, "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", "score": 100, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 5, "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", "score": 100, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 6, "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", "score": 96.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 96.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 8, "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", "score": 95.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 9, "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", "score": 88.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 10, "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", "score": 87.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 11, "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", "score": 84.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 12, "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", "score": 84.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 13, "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", "score": 84, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 33, "scoreConfidence": 3 }, { "rank": 14, "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", "score": 83.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 15, "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", "score": 82.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 16, "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", "score": 82.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 82.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 18, "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", "score": 82.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 19, "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", "score": 82, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 81.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 21, "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", "score": 79.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 22, "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", "score": 79.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 23, "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", "score": 79.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 79.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 77.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 26, "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", "score": 74.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 27, "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", "score": 72.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 28, "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", "score": 71.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 29, "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", "score": 71.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 30, "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", "score": 71.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 70.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 32, "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", "score": 70.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 33, "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", "score": 70.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 34, "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", "score": 68.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 68.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 36, "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", "score": 68.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 37, "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", "score": 67.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 38, "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", "score": 67.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 39, "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", "score": 67, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 67, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 66.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 66.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 64.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 44, "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", "score": 64.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 63.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 63.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 63.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 62.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 62.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 62.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 61.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 61.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 60.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 59.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 58.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 58.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 57.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 57.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 56, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 50.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 48.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 46.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 45.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 44.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 43.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 43.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 42, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 40.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 40.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 39.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 38.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 36.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 35.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 35.3, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 33.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 33.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 32.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 32.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 32.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 31.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 26.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 25.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 24.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 22.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 13.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 11.2, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 11.1, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 8.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 7.5, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 7.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 6.4, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 5.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 4.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 4.7, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 4.6, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 2.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 1.9, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 1.8, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 0, "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "instructionFollowing": [ { "rank": 1, "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", "score": 100, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 2, "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", "score": 100, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 3, "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", "score": 98.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 4, "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", "score": 96, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 5, "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", "score": 96, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 6, "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", "score": 95.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 7, "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", "score": 95.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 8, "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", "score": 95.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 9, "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", "score": 93.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 10, "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", "score": 93.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 11, "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", "score": 93.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 33, "scoreConfidence": 3 }, { "rank": 12, "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", "score": 92.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 13, "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", "score": 92.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 14, "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", "score": 92, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 15, "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", "score": 91.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 38, "scoreConfidence": 4 }, { "rank": 16, "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", "score": 91.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 91.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 18, "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", "score": 91.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 19, "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", "score": 90.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 89, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 21, "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", "score": 87.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 22, "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", "score": 87.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 23, "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", "score": 86.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 24, "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", "score": 85.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 84.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 26, "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", "score": 84.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 27, "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", "score": 84.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 28, "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", "score": 84.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 29, "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", "score": 84.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 83.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 82.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 32, "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", "score": 82.1, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 81.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 81.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 35, "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", "score": 81, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 80.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 37, "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", "score": 80.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 38, "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", "score": 79.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 39, "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", "score": 79.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 40, "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", "score": 79.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 78.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 78, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 43, "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", "score": 76.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 44, "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", "score": 76.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 76.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 76.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 47, "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", "score": 76.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 75.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 74.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 72.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 72.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 52, "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", "score": 71.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 15, "scoreConfidence": 3 }, { "rank": 53, "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", "score": 69.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 69.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 69.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 67, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 66.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 65.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 65.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 65.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 65.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 63.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 63.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 64, "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", "score": 62.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 62.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 62.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 62.1, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 61.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 61.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 59.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 59, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 58.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 58.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 58.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 58.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 58.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 54.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 54.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 54.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 54.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 54.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 52.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 50.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 48.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 47.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 47.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 46.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 88, "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", "score": 46.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 44.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 11, "scoreConfidence": 1 }, { "rank": 90, "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", "score": 44, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 44, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 92, "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", "score": 44, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 42.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 41.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 40.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 40.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 97, "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", "score": 40.3, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 38.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 99, "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", "score": 38, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 36.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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", "score": 36.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 36.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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", "score": 36.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "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", "score": 36.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 36.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 34.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 107, "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", "score": 33.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 108, "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", "score": 33, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 109, "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", "score": 32.2, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 110, "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", "score": 31.9, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 14, "scoreConfidence": 1 }, { "rank": 111, "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", "score": 26.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 112, "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", "score": 22.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 113, "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", "score": 18.8, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 114, "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", "score": 18.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 115, "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", "score": 14.6, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 116, "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", "score": 14.1, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 117, "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", "score": 11.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 118, "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", "score": 9.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 119, "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", "score": 8.5, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 120, "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", "score": 5.4, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 121, "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", "score": 3.7, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 122, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 123, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 124, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 125, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 126, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 127, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 128, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 129, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 130, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 131, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 132, "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", "score": 0, "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "math": [ { "rank": 1, "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", "score": 100, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 2, "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", "score": 99.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 3, "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", "score": 97.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 4, "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", "score": 97.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 5, "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", "score": 94.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 6, "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", "score": 94.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 7, "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", "score": 94.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 26, "scoreConfidence": 4 }, { "rank": 8, "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", "score": 94.1, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 9, "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", "score": 93.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 10, "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", "score": 92.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 11, "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", "score": 92.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 12, "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", "score": 91.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 13, "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", "score": 91.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 14, "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", "score": 90.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 15, "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", "score": 89.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 16, "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", "score": 87.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 17, "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", "score": 86.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 18, "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", "score": 86.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 27, "scoreConfidence": 4 }, { "rank": 19, "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", "score": 83.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 20, "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", "score": 82.1, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 81.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 22, "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", "score": 80.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 23, "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", "score": 80.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 24, "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", "score": 80, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 78.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 26, "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", "score": 76.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 27, "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", "score": 76.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 75.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 29, "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", "score": 74.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 30, "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", "score": 73.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 73.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 36, "scoreConfidence": 4 }, { "rank": 32, "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", "score": 70.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 33, "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", "score": 70.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 70.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 70.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 36, "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", "score": 68.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 37, "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", "score": 67.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 38, "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", "score": 67.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 39, "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", "score": 64.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 64.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 61.1, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 42, "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", "score": 58, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 56.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 44, "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", "score": 55, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 54.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 46, "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", "score": 52.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 47, "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", "score": 52.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 52.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 49, "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", "score": 52, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 51.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 51, "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", "score": 51.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 50.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 53, "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", "score": 47.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 46.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 55, "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", "score": 45.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 45.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 43.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 58, "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", "score": 42.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 59, "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", "score": 42, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "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", "score": 40.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "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", "score": 39.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "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", "score": 37.2, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 37.1, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 37, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 14, "scoreConfidence": 1 }, { "rank": 65, "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", "score": 36.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 34.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 67, "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", "score": 33.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 32.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 31.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 70, "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", "score": 31, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 71, "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", "score": 27.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 27.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 26.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 24.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 75, "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", "score": 18.8, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "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", "score": 15.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 13.4, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 78, "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", "score": 10.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 79, "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", "score": 10.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 80, "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", "score": 9.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 7.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 82, "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", "score": 7.3, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 5.5, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 3.6, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 85, "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", "score": 1.9, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 86, "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", "score": 1.7, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 1.1, "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ] } }