DeepSeek · Jul 31, 2026
Source confirmed
LLM leaderboard, July 2026
LLM Leaderboard & AI Model Benchmarks — July 2026
Compare frontier AI models by quality, cost, and context. 103 Supported and 111 Estimated models among 297 tracked LLMs — 376 benchmarks, real pricing, and runtime data in one place.
- Data refreshed
- July 31, 2026
- Supported
- 103 models
- Ranking method
- BenchAlign v5.2
Thinking Machines Lab · Jul 30, 2026
Source confirmed
Alibaba · Jul 27, 2026
Source confirmed
Decision-ready picks
Current models that clear the ranking, freshness, and evidence thresholds for each decision.
DecisionModelCurrent measureProvenance
- Best open weightHighest-scoring evidence-qualified current open-weight model.MiniMax M3MiniMax68.76overall scoreSupported · 2 source families
- Best near-frontier value91% of the leading score at a lower output price.Grok 4.5xAI$6output / 1M tokensSupported · 3 source families
- Fastest measuredFastest externally measured model that also clears the ranking and evidence thresholds.Grok 4.20xAI233tokens / secArtificial Analysis · updated 2026-07-31
- Largest useful contextLargest context among evidence-qualified current models retaining at least half of the leading score.Grok 4.20xAI2Mcontext windowEstimated · 1 source family
The LLM leaderboard — July 2026 rankings
Benchmarks, pricing, runtime signals, and context window in one table. Filter state syncs to the URL so every view is shareable. Supported and Estimated labels show how much independent evidence backs each position.
297 models
Every row can rank. Supported positions have diverse direct evidence; Estimated positions remain visible with wider uncertainty.Supporteddiverse direct evidenceEstimatedlimited direct coverage
1 Claude Mythos 5 AnthropicSupported | Anthropic | Closed | Current | Reasoning | 1M+ | $10.00 / $50.00 | Not measured | Not measured | 82.98 | 66 | 80 | — | 86 | 94 | — | — | — | — |
2 Claude Opus 5 AnthropicSupported | Anthropic | Closed | Current | Reasoning | — | $5.00 / $25.00 | Not measured | Not measured | 82.79 | 72 | 78 | 93 | 89 | 94 | — | — | — | 1494.88 |
3 Claude Fable 5 AnthropicSupported | Anthropic | Closed | Current | Reasoning | 1M+ | $10.00 / $50.00 | Not measured | Not measured | 82.73 | 65 | 80 | — | 64 | 71 | — | — | — | 1508.02 |
4 GPT-5.6 Sol OpenAISupported | OpenAI | Closed | Current | Reasoning | 1.05M | $5.00 / $30.00 | Not measured | Not measured | 81.36 | 76 | 78 | 94 | 85 | 83 | — | — | 97 | 1484.91 |
5 Kimi K3 Moonshot AISupported | Moonshot AI | Closed | Current | Reasoning | 1.05M | $3.00 / $15.00 | Not measured | Not measured | 79.87 | 67 | 77 | — | 90 | 85 | — | — | — | 1485.33 |
6 Claude Opus 4.8 AnthropicSupported | Anthropic | Closed | Superseded | Reasoning | 1M | $5.00 / $25.00 | Not measured | Not measured | 77.42 | 63 | 70 | 77 | 90 | 88 | — | — | 67 | 1484.03 |
7 Muse Spark 1.1 MetaSupported | Meta | Closed | Current | Reasoning | 1M | Not listed | Not measured | Not measured | 76.34 | 68 | 64 | — | 80 | 94 | — | — | — | 1492.72 |
8 Grok 4.5 xAISupported | xAI | Closed | Current | Reasoning | 500K | $2.00 / $6.00 | Not measured | Not measured | 75.48 | 61 | 58 | 61 | 69 | 70 | — | — | — | 1467.88 |
9 Gemini 3.6 Flash GoogleSupported | Closed | Current | Reasoning | 1M | $1.50 / $7.50 | Not measured | Not measured | 75.27 | 46 | 64 | — | 75 | 71 | — | — | — | 1482.49 | |
10 GPT-5.4 OpenAISupported | OpenAI | Closed | Superseded | Reasoning | 1.05M | $2.50 / $15.00 | 74 | 151.79s | 73.24 | 56 | 58 | 79 | 69 | 77 | — | — | 66 | 1465.47 |
11 GPT-5.5 OpenAIEstimated | OpenAI | Closed | Superseded | Reasoning | 1M | $5.00 / $30.00 | Not measured | Not measured | 72.01 | 64 | 71 | 88 | 69 | 79 | — | — | 71 | 1481.63 |
12 GPT-5.6 Terra OpenAIEstimated | OpenAI | Closed | Current | Reasoning | 1.05M | $2.00 / $12.00 | Not measured | Not measured | 71.97 | 73 | 65 | 87 | 76 | 82 | — | — | 97 | — |
13 Qwen3.7 Max AlibabaSupported | Alibaba | Closed | Superseded | Reasoning | 1M | Not listed | Not measured | Not measured | 71.78 | 41 | 54 | 88 | — | 72 | 100 | 91 | 82 | 1474.62 |
14 Claude Opus 4.7 (Adaptive) AnthropicEstimated | Anthropic | Closed | Superseded | Reasoning | 1M | $5.00 / $25.00 | Not measured | Not measured | 71.5 | 64 | 64 | 80 | 50 | 83 | — | — | — | 1502.4 |
15 Claude Opus 4.7 AnthropicSupported | Anthropic | Closed | Current | Standard | 1M | $5.00 / $25.00 | Not measured | Not measured | 71.25 | 55 | 68 | — | — | 63 | — | — | 62 | 1493.23 |
16 Muse Spark MetaSupported | Meta | Closed | Superseded | Reasoning | 262K | Not listed | Not measured | Not measured | 70.36 | 58 | 63 | 53 | 77 | 75 | — | — | 56 | 1487.88 |
17 MiMo-V2.5-Pro XiaomiSupported | Xiaomi | Closed | Current | Reasoning | 1M | Not listed | Not measured | Not measured | 69.19 | 42 | 55 | — | — | 71 | — | — | — | 1465.69 |
18 | MiniMax | Open | Current | Standard | 1M | $0.30 / $1.20 | Not measured | Not measured | 68.76 | 41 | 48 | — | 48 | 66 | — | — | — | 1445.02 |
| Tencent | Open | Current | Reasoning | 256K | $0.00 / $0.00 | Not measured | Not measured | 67.97 | 61 | 63 | — | — | — | — | — | — | 1457.31 | |
20 Claude Opus 4.6 AnthropicSupported | Anthropic | Closed | Superseded | Standard | 1M | $5.00 / $25.00 | 40 | 1.78s | 67.74 | 56 | 61 | — | 62 | 83 | — | — | 60 | 1497.57 |
| Z.AI | Open | Superseded | Reasoning | 203K | $1.40 / $4.40 | Not measured | Not measured | 66.84 | 49 | 56 | — | — | 78 | — | — | 65 | 1469.08 | |
22 Gemini 3 Pro GoogleSupported | Closed | Established | Standard | 2M | $2.00 / $12.00 | 109 | 32.65s | 66.81 | 58 | 61 | 43 | 74 | 69 | — | — | 57 | 1485.67 | |
23 MiMo-V2-Pro XiaomiSupported | Xiaomi | Closed | Superseded | Reasoning | 1M | Not listed | Not measured | Not measured | 66.75 | — | 61 | — | — | — | — | — | — | 1448.39 |
| Thinking Machines Lab | Open | Current | Standard | 1M | $1.87 / $4.68 | Not measured | Not measured | 66.59 | 46 | 44 | — | 53 | 69 | — | 89 | 79 | 1442.3 | |
25 GPT-5.6 Luna OpenAIEstimated | OpenAI | Closed | Current | Reasoning | 1.05M | $0.20 / $1.20 | Not measured | Not measured | 66.56 | 58 | 72 | 67 | 67 | 81 | — | — | 97 | — |
Showing 25 of 297
The BenchLM LLM leaderboard 2026 ranks 214+ models and tracks 297+ large language models side by side across 376 benchmarks — from SWE-bench and LiveCodeBench for coding to GPQA Diamond and MMLU-Pro for knowledge and reasoning. Whether you need the best AI models 2026 has to offer for agentic workflows, math, multilingual tasks, or instruction following, our AI benchmark comparison tables make it easy to see how GPT-5, Claude, Gemini, DeepSeek, Llama, and dozens of other frontier and open-source models stack up on both benchmarks and operator tradeoffs like price and context. Supported and Estimated labels separate evidence strength from score, so incomplete reporting does not automatically remove a model from the comparison.
Dataset journal
What changed in July 2026
- Claude Mythos 5 (Anthropic) holds the #1 spot on the BenchAlign leaderboard at 82.98.
- 30 model releases tracked in July 2026.
- Google climbed 3 spots in the provider race.
- 103 Supported and 111 Estimated models appear in the public leaderboard.
Data verified
Build a head-to-head comparison
Choose any two ranked models. The comparison opens with the decision, exact units, and evidence coverage.
versusCompare these models
The evidence map
Explore benchmarks by category
Move from the overall ranking into the capability or workload that actually decides your model choice.
Agentic80Tools, browsers, and long-running workCoding52Repository tasks and code generationMultimodal64Documents, images, and grounded workReasoning26Long-context and abstract reasoningKnowledge46Professional and scientific knowledgeInstruction following4Constraint and format reliabilityMultilingual13Cross-language accuracy and coverageMath32Contest and frontier mathematics
More ranking paths
Choose by workload
Long ContextLongBench v2, MRCR, AI-Needle, GraphwalksTool UseBFCL, MCP Atlas, Toolathlon, TAU BenchWeb ResearchBrowseComp, WebArena, WebVoyagerComputer UseOSWorld, ScreenSpot Pro, Vision2WebDocument AIOfficeQA Pro, OmniDocBench, CC-OCRImage UnderstandingMMMU-Pro, AI2D, CountBench, RefCOCOFrontend / App DevReact Native Evals, Design2Code, Vision2WebFactualitySimpleQA, HLE w/o tools, Facts-VLM
Six-month release record
The AI race, read as a record instead of a spectacle
Track which release led its month, how provider depth changed, and whether the crown moved.
- Months
- 6
- Releases
- 165
- Lead changes
- 5
Best ranked model released in Jul 2026
Claude Opus 5AnthropicScore82.79
RankProviderTop-three avg.Models
01Anthropic82.820
02OpenAI75.538
03Google69.117
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.
Popular comparisons
Tools and resources
AI Prompt WriterTurn the work you need into a testable promptPrompt OptimizerGet closer to usable output with a clearer promptLLM Pricing ComparisonCompare API costs across modelsAlternative FinderFind the best ChatGPT or Claude replacementWhich LLM Should I Use?Get a personalized recommendationCost CalculatorEstimate your monthly API spendMethodology & ExplainersHow BenchLM scores and curates benchmarks
Scoring methodology
Scoring methodology8 weighted categories, 27 ranking benchmarks, and 290 display-only records.Inspect method
Each model's overall score is a normalized weighted average of category averages. Within each category, benchmark results are normalized to a common scale and combined using weights that favor harder, less-saturated evaluations.
Confidence remains separate from score. It shows how much public benchmark evidence supports a result, while display-only benchmarks stay visible for context without receiving ranking weight.
Data comes from OpenBench, official model papers, and public leaderboards. External consensus signals are bounded calibration inputs and are not exposed in exported data.
Read the complete methodology- Category weights
- 100%
- Scored categories
- 8
- Ranking benchmarks
- 27
- Display-only
- 290
Category and weightBenchmarks that affect the scoreCoverage
- Agentic22%
Terminal-Bench 2.0 · BrowseComp · OSWorld-Verified
3 weighted · 77 context-only
- Coding20%
SWE-bench Verified · SWE-Rebench · LiveCodeBench · SWE-bench Pro · SciCode
5 weighted · 47 context-only
- Reasoning17%
LongBench v2 · MRCRv2 · ARC-AGI-2
3 weighted · 23 context-only
- Multimodal12%
MMMU-Pro · OfficeQA Pro · CharXiv
3 weighted · 61 context-only
- Knowledge12%
GPQA · SuperGPQA · MMLU-Pro · HLE · SimpleQA
5 weighted · 41 context-only
- Multilingual7%
MMLU-ProX
1 weighted · 12 context-only
- Instruction Following5%
IFEval · IFBench
2 weighted · 2 context-only
- Math5%
AIME26 · HMMT Feb 2026 · FrontierMath v2 (Tiers 1-3) · FrontierMath v2 (Tier 4) · USAMO 2026
5 weighted · 27 context-only