Claude Opus 4.1 ranks first on CompileBench.
Closed weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Lech Mazur Creative Writing | 8.47 | #3 of 44 | Epoch AI | |
| Phare | 76.9% | #5 of 62 | Official leaderboard | |
| MMMLU | 89.5% | #10 of 62 | Model card | |
| LMArena (Elo) | 1,450 | #62 of 333 | Official leaderboard | |
| Global MMLU Lite | 94.3% | #9 of 43 | Official leaderboard | |
| WritingBench | 76.4 | #15 of 45 | Official leaderboard | |
| BullshitBench | 40% | #36 of 107 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 70.5 | #42 of 119 | Official leaderboard | |
| IndicGenBench | 55.0 | #5 of 13 | Official leaderboard | |
| MultiNRC | 38.4% | #16 of 38 | Official leaderboard | |
| BullshitBench V2 | 43% | #54 of 122 | Official leaderboard | |
| LLM Confabulation Leaderboard | 17.1% | #30 of 58 | Official leaderboard | |
| SimpleQA Verified | 31% | #29 of 56 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 4.20% | #81 of 148 | Official leaderboard | |
| MultiChallenge | 57.2% | #20 of 35 | Official leaderboard | |
| Humanity's Last Exam | 11.5% | #27 of 47 | Official leaderboard | |
| FACTS Parametric | 33.2% | #26 of 45 | Official leaderboard | |
| FACTS Search | 65% | #21 of 31 | Official leaderboard | |
| FACTS Multimodal | 33.1% | #28 of 39 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 11.8% | #76 of 104 | Official leaderboard | |
| FACTS Benchmark Suite | 33.1% | #34 of 40 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CORE-Bench | 51.1% | #3 of 17 | Official leaderboard | |
| SimpleBench | 60% | #39 of 100 | Official leaderboard | |
| GPQA Diamond | 77.3% | #93 of 219 | Epoch AI | |
| DTBench | 66.7% | #90 of 178 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 68.9% | #103 of 202 | Epoch AI | |
| FrontierMath Tier 4 | 4.17% | #31 of 55 | Epoch AI | |
| FrontierMath | 7.24% | #41 of 70 | Epoch AI | |
| AIME 2025 | 78% | #96 of 143 | Model card | |
| ForecastBench | 63.9 | #58 of 86 | Official leaderboard | |
| FrontierMath Tier 4 v2 | 2.44% | #64 of 71 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 12.6% | #83 of 89 | Epoch AI | |
| IMProofBench | 3.38% | #10 of 10 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ArtifactsBench | 59.8% | #2 of 20 | Official leaderboard | |
| METR Time Horizon | 109 min | #5 of 31 | Official leaderboard | |
| METR Time Horizon 1.1 | 100 min | #12 of 26 | Official leaderboard | |
| SWE-fficiency | 9.84% | #8 of 17 | Official leaderboard | |
| WeirdML | 45.9% | #58 of 112 | Official leaderboard | |
| SWE-bench Verified (hard subset) | 43.8% | #5 of 9 | Model card | |
| IOI (Vals) | 12.5% | #31 of 55 | Official leaderboard | |
| SWE-bench Verified | 73.3% | #20 of 32 | Epoch AI | |
| WebDev Arena | 1,389 | #71 of 105 | Epoch AI | |
| ALE-Bench | 675 | #84 of 121 | Epoch AI | |
| Code Arena | 1,390 | #87 of 124 | Official leaderboard | |
| Quadruped reinforcement learning task (Anthropic) | 1.18 | #7 of 8 | Model card | |
| AlgoTune | 1.34× | #16 of 18 | Official leaderboard | |
| Time series forecasting task (Anthropic) | 6.54 | #9 of 9 | Model card | |
| Text-based reinforcement learning task (Anthropic) | 0.42 | #7 of 7 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CompileBench | 100% | #1 of 20 | Official leaderboard | |
| Elimination Game | 5 | #10 of 56 | Official leaderboard | |
| tau-bench | 69.2% | #5 of 23 | Model card | |
| Terminal-Bench | 38% | #4 of 18 | Epoch AI | |
| MCP-Universe | 29.4% | #8 of 30 | Official leaderboard | |
| MCPMark | 29.9% | #9 of 28 | Official leaderboard | |
| Step Race | 3 | #21 of 59 | Official leaderboard | |
| DeepResearch Bench | 48.3% | #9 of 24 | Epoch AI | |
| Mystery Game Puzzles | 21% | #43 of 80 | Epoch AI | |
| LLM Chess | -38 | #67 of 124 | Official leaderboard | |
| LisanBench | 394.7 | #72 of 133 | Official leaderboard | |
| Terminal-Bench 2.0 | 38% | #25 of 43 | Official leaderboard | |
| LMArena Search Arena | 1,167 | #30 of 35 | Official leaderboard | |
| LiveResearchBench | 61.8 | #6 of 7 | Official leaderboard | |
| EBR-bench | 7.94% | #25 of 28 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent v1 | 50.9% | #6 of 47 | Official leaderboard | |
| GDPval | 43.6% | #3 of 11 | Epoch AI | |
| MedCode | 47.2% | #34 of 96 | Official leaderboard | |
| TaxEval v2 | 73.7% | #46 of 129 | Official leaderboard | |
| LegalBench | 83.5% | #54 of 138 | Official leaderboard | |
| MortgageTax | 61.1% | #59 of 86 | Official leaderboard | |
| TaxCalcBench | 28.4% | #13 of 17 | Official leaderboard | |
| MedScribe | 73.9% | #76 of 98 | Official leaderboard | |
| PRBench | 34% | #42 of 44 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 77.1% | #16 of 136 | Official leaderboard | |
| MATH-Vision (MathVision) | 66% | #28 of 105 | Official leaderboard | |
| VISTA | 48.4% | #15 of 54 | Official leaderboard | |
| Math-VR | 54.3% | #8 of 26 | Official leaderboard | |
| EnigmaEval | 7.18% | #18 of 41 | Epoch AI | |
| ZeroBench | 8.00% | #32 of 66 | Official leaderboard | |
| VPCT | 35% | #23 of 28 | Epoch AI | |
| ClockBench | 8.90% | #31 of 37 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BBQ (Bias Benchmark for QA) | 90.7% | #4 of 24 | Model card | |
| FORTRESS | 14.8% | #12 of 66 | Official leaderboard | |
| Cybench | 42% | #8 of 24 | Official leaderboard | |
| LAB-Bench CloningScenarios | 56% | #4 of 11 | Model card | |
| Single-turn harmful request evaluations (Anthropic) | 98.8% | #7 of 18 | Model card | |
| Single-turn benign request evaluations (Anthropic) | 0.08% | #9 of 18 | Model card | |
| CyberGym | 25% | #23 of 33 | Official leaderboard | |
| Creative biology | 48% | #5 of 7 | Model card | |
| LAB-Bench SeqQA | 71% | #9 of 12 | Model card | |
| LAB-Bench ProtocolQA | 69% | #12 of 15 | Model card | |
| Impossible tasks (Anthropic) | 52% | #9 of 11 | Model card | |
| LAB-Bench FigQA | 46% | #9 of 10 | Model card | |
| Reward-hack-prone coding tasks (Anthropic) | 12% | #8 of 8 | Model card | |
| Average in-eval reward hacking rate (Anthropic) | 18.2% | #5 of 5 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 37.1% | #64 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 48.3 | #75 of 149 | Official leaderboard | |
| ACCoRD | 63.5 | #78 of 150 | Official leaderboard | |
| SAGE (Vals) | 31.4% | #72 of 81 | Official leaderboard |
Anthropic's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it. 29 of them aren't in the launch post.