- Agentic coding SWE-bench Verified 80.9
- Agentic terminal coding Terminal-bench 2.0 (128k thinking budget) 59.3
- Mean of Agentic tool use τ2-bench Retail / Agentic tool use τ2-bench Telecom 93.6
- Scaled tool use MCP Atlas 62.3
- Computer use OSWorld 66.3
- Novel problem solving ARC-AGI-2 (Verified) 37.6
- Graduate-level reasoning GPQA Diamond 87
- Visual reasoning MMMU (validation) 80.7
- Multilingual Q&A MMMLU 90.8
Claude Opus 4.5
Claude Opus 4.5 ranks first on 18 of the 176 benchmarks it has scores on.
185
Benchmarks with a score
18
Ranked first, out of five or more models
34
In the top three
Anthropic Nov 2025
Claude Opus 4.5
Closed weights Flagship
150.2
#62 of 271
Epoch Capabilities Index
- Humanity's Last Exam 25.2% #16 /47
- SWE-bench Verified 76.7% #9 /32
- SWE-Bench Pro 45.9% #6 /24
Where it ranks
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Phare | 82.4% | #2 of 62 | Official leaderboard | |
| BullshitBench V2 | 90% | #4 of 122 | Official leaderboard | |
| BullshitBench | 90.9% | #4 of 107 | Official leaderboard | |
| MMLU-Pro | 87.3% | #13 of 212 | Official leaderboard | |
| LMArena (Elo) | 1,474 | #36 of 333 | Official leaderboard | |
| MMMLU | 90.8% | #7 of 62 | Model card | |
| False-premise questions (Anthropic) | 1.20% | #1 of 6 | Model card | |
| AA-Omniscience | 51.9% | #3 of 17 | Model card | |
| WritingBench | 79.8 | #8 of 45 | Official leaderboard | |
| CL-bench | 21.1% | #5 of 24 | Official leaderboard | |
| EQ-Bench 3 | 1,522 | #20 of 78 | Official leaderboard | |
| Creative Writing v3 | 75.0 | #31 of 120 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 73.1 | #32 of 119 | Official leaderboard | |
| MultiNRC | 48.6% | #12 of 38 | Official leaderboard | |
| LOCA-Bench | 14.7% | #3 of 9 | Official leaderboard | |
| Humanity's Last Exam | 25.2% | #16 of 47 | Official leaderboard | |
| FACTS Search | 73.3% | #12 of 31 | Official leaderboard | |
| 100Q-Hard (Anthropic) | 45.9% | #3 of 7 | Model card | |
| SimpleQA Verified | 39% | #25 of 56 | Official leaderboard | |
| Document Arena | 1,465 | #17 of 37 | Official leaderboard | |
| MultiChallenge | 59% | #18 of 35 | Official leaderboard | |
| FACTS Multimodal | 39.2% | #23 of 39 | Official leaderboard | |
| FACTS Parametric | 30.6% | #28 of 45 | Official leaderboard | |
| Extended NYT Connections | 52.5% | #64 of 97 | Official leaderboard | |
| SkateBench v2 | 50.3% | #14 of 21 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 10.9% | #72 of 104 | Official leaderboard | |
| FACTS Benchmark Suite | 39.2% | #30 of 40 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CORE-Bench | 77.8% | #1 of 17 | Official leaderboard | |
| AIME 2025 | 92.8% | #36 of 143 | Model card | |
| DTBench | 83.1% | #50 of 178 | Official leaderboard | |
| SimpleBench | 62% | #30 of 100 | Official leaderboard | |
| GPQA Diamond | 86% | #67 of 219 | Epoch AI | |
| ProofBench | 36% | #20 of 59 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 86.1% | #76 of 202 | Epoch AI | |
| FrontierMath | 20.7% | #30 of 70 | Epoch AI | |
| ARC-AGI-2 | 37.6% | #45 of 95 | Official leaderboard | |
| ARC-AGI | 80% | #45 of 92 | Official leaderboard | |
| FrontierMath Tier 4 | 4.17% | #33 of 55 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 34.4% | #65 of 89 | Epoch AI | |
| IMO-ProofBench | 23.8% | #8 of 10 | Official leaderboard | |
| ForecastBench | 64.8 | #73 of 86 | Official leaderboard | |
| FrontierMath Tier 4 v2 | 4.88% | #62 of 71 | Epoch AI | |
| LABBench2 | 47.1% | #5 of 5 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| METR Time Horizon | 4.1 h | #1 of 31 | Official leaderboard | |
| SWE-fficiency | 22.5% | #1 of 17 | Official leaderboard | |
| OTelBench | 29% | #1 of 14 | Official leaderboard | |
| SWE-bench | 52.6% | #1 of 9 | Official leaderboard | |
| Text-based reinforcement learning task (Anthropic) | 0.97 | #1 of 7 | Model card | |
| Internal model use survey (Anthropic) | 50% | #1 of 5 | Model card | |
| WeirdML | 63.7% | #26 of 112 | Official leaderboard | |
| OpenHands Index | 60.6% | #8 of 33 | Official leaderboard | |
| SWE-Bench Pro | 45.9% | #6 of 24 | Official leaderboard | |
| METR Time Horizon 1.1 | 4.9 h | #7 of 26 | Official leaderboard | |
| AlgoTune | 1.77× | #5 of 18 | Official leaderboard | |
| SWE-bench Verified | 76.7% | #9 of 32 | Epoch AI | |
| SWE-bench Verified (hard subset) | 46.7% | #3 of 9 | Model card | |
| IOI (Vals) | 23.6% | #19 of 55 | Official leaderboard | |
| SWE-bench Multilingual | 76.2% | #25 of 70 | Model card | |
| GSO-Bench | 26.5% | #12 of 30 | Official leaderboard | |
| Vibe Code Bench v1 | 20.6% | #7 of 17 | Official leaderboard | |
| WebDev Arena | 1,495 | #45 of 105 | Epoch AI | |
| ALE-Bench | 1,025 | #52 of 121 | Epoch AI | |
| Code Arena | 1,494 | #58 of 124 | Official leaderboard | |
| Internal AI research evaluation suite 2 | 0.60 | #3 of 6 | Model card | |
| PostTrainBench | 17.3% | #13 of 23 | Official leaderboard | |
| SlopCodeBench | 17.4% | #8 of 14 | Official leaderboard | |
| TasteVal | 11.8× | #14 of 20 | Official leaderboard | |
| Vibe Code Bench | 20.6% | #81 of 115 | Official leaderboard | |
| WeirdML v3 | 6.51% | #20 of 25 | Official leaderboard | |
| Vals RSI Index | 0.15 | #24 of 25 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 77.5% | #1 of 65 | Official leaderboard | |
| Elimination Game | 6 | #4 of 56 | Official leaderboard | |
| tau2-bench | 93.6% | #8 of 69 | Model card | |
| DeepResearch Bench | 54.8% | #3 of 24 | Epoch AI | |
| MCPMark | 42.3% | #4 of 28 | Official leaderboard | |
| LisanBench | 5513.0 | #22 of 133 | Official leaderboard | |
| SnakeBench | 30 | #36 of 183 | Official leaderboard | |
| VITA-Bench | 28.5% | #4 of 18 | Official leaderboard | |
| OSWorld | 66.3% | #2 of 9 | Epoch AI | |
| ITBench | 52.1% | #3 of 13 | Official leaderboard | |
| Terminal-Bench 2.0 | 63.1% | #10 of 43 | Official leaderboard | |
| OSWorld-Verified | 76.3% | #8 of 33 | Official leaderboard | |
| GAIA | 74.1% | #14 of 57 | Official leaderboard | |
| BalatroBench | 13.9 | #4 of 16 | Official leaderboard | |
| BrowseComp-Plus | 67.6% | #1 of 4 | Model card | |
| BALROG | 43.5% | #10 of 35 | Official leaderboard | |
| tau3-bench | 85.3% | #2 of 7 | Official leaderboard | |
| Toolathlon | 43.5% | #15 of 50 | Official leaderboard | |
| PinchBench | 72.5% | #16 of 48 | Official leaderboard | |
| LLM Chess | 446 | #42 of 124 | Official leaderboard | |
| Step Race | 3 | #20 of 59 | Official leaderboard | |
| Pencil Puzzle Bench | 6.70% | #20 of 53 | Official leaderboard | |
| RWSearch | 75.5% | #3 of 7 | Official leaderboard | |
| WebArena | 65.3% | #4 of 8 | Model card | |
| Mystery Game Puzzles | 22% | #41 of 80 | Epoch AI | |
| SkillsBench | 49% | #12 of 21 | Official leaderboard | |
| Game Arena Four in a Row | 302 | #22 of 38 | Official leaderboard | |
| MCP Atlas | 69.8% | #22 of 34 | Official leaderboard | |
| Agent Poker Bench | 1,033 | #11 of 17 | Official leaderboard | |
| EBR-bench | 14.3% | #19 of 28 | Epoch AI | |
| Game Arena Chess Openings | 252 | #8 of 11 | Official leaderboard | |
| τ³-bench Banking | 24.7% | #19 of 25 | Official leaderboard | |
| LMArena Search Arena | 1,187 | #27 of 35 | Official leaderboard | |
| DeepSearchQA | 24% | #8 of 10 | Official leaderboard | |
| Chess Puzzles | 14% | #68 of 83 | Epoch AI | |
| Multi-agent search (Anthropic internal benchmark) | 74.8% | #1 of 1 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent v1 | 55.2% | #4 of 47 | Official leaderboard | |
| MortgageTax | 68.7% | #13 of 86 | Official leaderboard | |
| Vals Finance Agent | 58.8% | #8 of 49 | Official leaderboard | |
| GDPval | 45.5% | #2 of 11 | Epoch AI | |
| TaxEval v2 | 74.9% | #27 of 129 | Official leaderboard | |
| LegalBench | 84.6% | #31 of 138 | Official leaderboard | |
| MedCode | 49.2% | #25 of 96 | Official leaderboard | |
| ProfBench | 54.2% | #20 of 72 | Official leaderboard | |
| MedScribe | 85.3% | #28 of 98 | Official leaderboard | |
| CorpFin v2 | 65.1% | #35 of 119 | Official leaderboard | |
| FailureSensorIQ | 66.7% | #8 of 24 | Official leaderboard | |
| CaseLaw v2 | 62.6% | #18 of 53 | Official leaderboard | |
| TaxCalcBench | 36.3% | #9 of 17 | Official leaderboard | |
| Vending-Bench 2 | $4,967 | #36 of 66 | Official leaderboard | |
| PRBench | 44.2% | #24 of 44 | Official leaderboard | |
| Vending-Bench Arena | $4,143 | #19 of 32 | Official leaderboard | |
| Remote Labor Index | 3.75% | #11 of 17 | Official leaderboard | |
| SpreadsheetBench | 64.3% | #4 of 6 | Model card | |
| prinzbench | 14.0 | #25 of 26 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 80.7% | #6 of 136 | Official leaderboard | |
| OCR Arena | 1,791 | #1 of 11 | Official leaderboard | |
| MATH-Vision (MathVision) | 77.1% | #20 of 105 | Official leaderboard | |
| MMMU-Pro | 73.9% | #12 of 57 | Official leaderboard | |
| EnigmaEval | 11.9% | #11 of 41 | Epoch AI | |
| VISTA | 46.4% | #22 of 54 | Official leaderboard | |
| GeoBench | 75% | #20 of 48 | Official leaderboard | |
| ZeroBench | 9.00% | #31 of 66 | Official leaderboard | |
| VPCT | 40% | #16 of 28 | Epoch AI | |
| Drone-Bench | 59.2% | #11 of 19 | Official leaderboard | |
| Furniture Assembly Benchmark | 28.3% | #26 of 35 | Epoch AI | |
| VoxelBench | 1,358 | #48 of 56 | Official leaderboard | |
| BabyVision | 14.2% | #27 of 27 | Official leaderboard |
Safety and security
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SAGE (Vals) | 52.1% | #8 of 81 | Official leaderboard | |
| ACCoRD | 79.1 | #15 of 150 | Official leaderboard | |
| CAIS Risk Index | 41.6 | #17 of 65 | Official leaderboard | |
| Conceptual Reasoning Index | 59.1 | #40 of 149 | Official leaderboard | |
| LMCA | 44.5% | #41 of 139 | Epoch AI | |
| CAIS Text Capabilities Index | 32.3 | #31 of 66 | Official leaderboard | |
| CAIS Vision Capabilities Index | 45.4 | #38 of 53 | Official leaderboard |
Anthropic's models over time
Anthropic's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 68 of them aren't in the launch post.
System Card: Claude Opus 4.5 24 Nov 2025
Capabilities
- SWE-bench Verified 80.9
- Terminal-Bench 2.0 59.3
- tau2-bench
- MCP Atlas 62.3
- OSWorld-Verified 66.3
- ARC-AGI-2 37.6
- GPQA Diamond 87
- MMMU 80.7
- MMMLU 90.8
- SWE-Bench Pro 51.6
- SWE-bench Multilingual 76.2
- BrowseComp-Plus 67.6
- Multi-agent search (Anthropic internal benchmark) 74.8
- ARC-AGI 80
- Vending-Bench 2 4967.1
- Vals Finance Agent 55.2
- CyberGym 50.6
- SpreadsheetBench 64.3
- Humanity's Last Exam 30.8
- AIME 2025 92.8
- LAB-Bench FigQA 54.9
- WebArena 65.3
Hallucination
- 100Q-Hard (Anthropic) 45.9
- SimpleQA Verified 44.1
- AA-Omniscience 51.9
- False-premise questions (Anthropic) 1.2
Safety
Robustness
Alignment
- Anthropic automated behavioral audit
- Petri
- Sycophancy on user-provided prompts (Anthropic) 10
- Agentic misalignment suite (Anthropic)
- Self-preference bias (Anthropic)
- Internal codebase sabotage propensity (Anthropic) 0
- Reward-hack-prone coding tasks (Anthropic) 0
- Impossible tasks (Anthropic) 55
- Training distribution hack rate (Anthropic) 1
- SHADE-Arena 7.7
- Subversion Strategy Eval
- UK AISI alignment and monitorability evaluations
Bio and chem risk
- Long-form virology tasks
- Virology Capabilities Test (VCT) 47.7
- DNA Synthesis Screening Evasion
- LAB-Bench ProtocolQA 90.7
- LAB-Bench SeqQA 85.2
- LAB-Bench CloningScenarios 75.8
- Creative biology 52.4
- Short-horizon computational biology tasks
- Bioinformatics evaluations (Anthropic) 73.7
- ASL-4 virology uplift trial (Anthropic) 66.8
Cyber risk
AI R&D risk
- SWE-bench Verified (hard subset) 46.7
- Kernels task (Anthropic) 252.4
- Time series forecasting task (Anthropic)
- Text-based reinforcement learning task (Anthropic) 0.975
- LLM training task (Anthropic) 16.5
- Quadruped reinforcement learning task (Anthropic)
- Novel compiler task (Anthropic)
- Internal AI research evaluation suite 2 0.604
- Internal model use survey (Anthropic) 50