Claude Opus 4.7
Claude / Anthropic
186scores
124benchmarks
$5 / $25 per 1M tokenscost in/out
Metadata
Claude Closed/API
Aliases: anthropic-claude-4.7-opus-20260416, anthropic-claude-opus-4.7, anthropic/claude-4.7-opus-20260416, anthropic/claude-opus-4.7, claude-4.7-opus-20260416, claude-opus-4.7
Official Sources
1 linked source| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| APEX-Agents | Agentic | 3 | 50.60 | 2026-05-06 |
| ARC-AGI-1 | Agentic | 5 | 93.5% | 2026-04-23 |
| ARC-AGI-2 | Agentic | 4 | 75.8% | 2026-04-23 |
| AutoBench | Agentic | 1 | 3.30 | 2026-05-06 |
| AutomationBench | Agentic | 3 | 9.9% | 2026-05-28 |
| AutomationBench | Agentic | 6 | 9.90 | 2026-05-21 |
| AutomationBench | Agentic | 9 | 8.40 | 2026-05-21 |
| AutomationBench | Agentic | 10 | 8.20 | 2026-05-21 |
| BrowseComp | Agentic | 4 | 79.8% | 2026-05-28 |
| BrowseComp | Agentic | 6 | 79.3% | 2026-04-23 |
| BrowseComp | Agentic | 5 | 79.3% | 2026-04-16 |
| GDPval-AA | Agentic | 3 | 1753 Elo | 2026-05-28 |
| Gert Labs Rankings | Agentic | 2 | 0.69 | 2026-05-11 |
| HiL-Bench | Agentic | 2 | 27.67% | 2026-05-05 |
| ITBench-AA | Agentic | 1 | 46.7% | 2026-05-28 |
| LMArena Search Arena | Agentic | 3 | 1233.14 | 2026-05-06 |
| MCP Atlas | Agentic | 2 | 79.1% | 2026-05-28 |
| MCP Atlas | Agentic | 1 | 79.10 | 2026-05-06 |
| MCP Atlas | Agentic | 1 | 79.1% | 2026-04-23 |
| MCP Atlas | Agentic | 1 | 77.3% | 2026-04-16 |
| OSWorld-Verified | Agentic | 2 | 82.8% | 2026-05-28 |
| OSWorld-Verified | Agentic | 3 | 0.78 | 2026-05-06 |
| OSWorld-Verified | Agentic | 2 | 78% | 2026-04-23 |
| OSWorld-Verified | Agentic | 2 | 78% | 2026-04-16 |
| RuneBench | Agentic | 4 | 4.60 | 2026-05-05 |
| ScreenSpot-Pro | Agentic | 2 | 87.6% | 2026-05-28 |
| Tau2-Bench Telecom | Agentic | 62 | 88.6% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 125 | 74% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 5 | 54.5% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 11 | 51.5% | 2026-05-11 |
| TERMS-Bench | Agentic | 3 | 66.0% SE+ | 2026-05-28 |
| Toolathlon | Agentic | 2 | 59.3% | 2026-05-28 |
| Vending-Bench 2 | Agentic | 1 | 10936.76 | 2026-05-28 |
| Vending-Bench 2 | Agentic | 1 | 10937 USD | 2026-05-28 |
| Vending-Bench 2 | Agentic | 2 | 7971 USD | 2026-05-28 |
| OpenUGI | Alignment | 31 | 56.53 | 2026-05-06 |
| OpenUGI | Alignment | 53 | 53.60 | 2026-05-06 |
| OpenUGI | Alignment | 75 | 51.79 | 2026-05-06 |
| OpenUGI | Alignment | 81 | 51.52 | 2026-05-06 |
| BioPipelineBench Verified | Biology | 3 | 83.6% | 2026-05-28 |
| LABBench2 Clinical Trials | Biology | 3 | 70.8% | 2026-05-28 |
| LABBench2 Patent Questions | Biology | 3 | 48.3% | 2026-05-28 |
| LABBench2 Reading Tables | Biology | 2 | 66.4% | 2026-05-28 |
| LABBench2 Supplementary Materials | Biology | 2 | 47.8% | 2026-05-28 |
| ProteinGym Hard | Biology | 3 | 37.7% | 2026-05-28 |
| Protocol Troubleshooting (Anthropic Internal) | Biology | 3 | 51.8% | 2026-05-28 |
| scBench | Biology | 3 | 55.3% | 2026-05-28 |
| scBench | Biology | 4 | 55.21% | 2026-05-27 |
| scBench | Biology | 5 | 54.02% | 2026-05-27 |
| SpatialBench | Biology | 3 | 51.4% | 2026-05-28 |
| SpatialBench | Biology | 5 | 52.41% | 2026-05-27 |
| SpatialBench | Biology | 7 | 51.36% | 2026-05-27 |
| Structural Biology Open-Ended | Biology | 3 | 74% | 2026-05-28 |
| Organic Chemistry (Anthropic Internal) | Chemistry | 3 | 77.2% | 2026-05-28 |
| Arena AI Code | Coding | 2 | 1561 | 2026-05-06 |
| BLXBench | Coding | 2 | 84.80 | 2026-05-06 |
| DeepSWE | Coding | 3 | 54.20 | 2026-05-26 |
| FrontierSWE | Coding | 2 | 4.2 avg rank | 2026-05-28 |
| IOI | Coding | 3 | 47.084% | 2026-05-26 |
| LiveCodeBench | Coding | 19 | 85.073% | 2026-05-28 |
| LMArena WebDev Arena | Coding | 2 | 1561.91 | 2026-05-06 |
| SciCode | Coding | 7 | 54.5% | 2026-05-11 |
| SciCode | Coding | 18 | 50.1% | 2026-05-11 |
| SWE-bench Verified | Coding | 3 | 82% | 2026-05-28 |
| Terminal-Bench 2.0 | Coding | 3 | 68.539% | 2026-05-28 |
| Terminal-Bench 2.0 | Coding | 3 | 69.4% | 2026-04-23 |
| Terminal-Bench 2.0 | Coding | 3 | 69.4% | 2026-04-16 |
| Terminal-Bench 2.1 | Coding | 5 | 68.539% | 2026-05-28 |
| Terminal-Bench 2.1 | Coding | 4 | 66.1% | 2026-05-28 |
| Vibe Code Bench v1.1 | Coding | 2 | 71.003% | 2026-05-28 |
| CyberGym | Cybersecurity | 3 | 73.1% | 2026-05-28 |
| CyberGym | Cybersecurity | 4 | 0.73 | 2026-05-06 |
| CyberGym | Cybersecurity | 3 | 73.1% | 2026-04-23 |
| CyberGym | Cybersecurity | 3 | 73.1% | 2026-04-16 |
| ExploitBench v8-bench | Cybersecurity | 5 | 3.66 points | 2026-05-28 |
| ExploitBench v8-bench | Cybersecurity | 6 | 3.46 points | 2026-05-28 |
| ExploitBench v8-bench | Cybersecurity | 7 | 3.66 points | 2026-05-15 |
| ExploitBench v8-bench | Cybersecurity | 9 | 3.46 points | 2026-05-15 |
| Firefox 147 JS Exploitation | Cybersecurity | 3 | 1.2% | 2026-05-28 |
| Arena AI Document | Document AI | 3 | 1515 | 2026-05-06 |
| OfficeQA (Anthropic Harness) | Document AI | 2 | 76.3% | 2026-05-28 |
| OfficeQA Pro | Document AI | 3 | 43.6% | 2026-04-23 |
| OfficeQA Pro (Anthropic Harness) | Document AI | 2 | 65% | 2026-05-28 |
| SAGE | Education | 1 | 56.103% | 2026-05-28 |
| AA-Omniscience | Factuality | 2 | 26.17 | 2026-05-11 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 74 | 88 | 2026-05-06 |
| CorpFin v2 | Finance | 11 | 66.084% | 2026-05-28 |
| Finance Agent v1.1 | Finance | 1 | 64.373% | 2026-05-04 |
| Finance Agent v1.1 | Finance | 1 | 64.4% | 2026-04-23 |
| Finance Agent v1.1 | Finance | 1 | 64.4% | 2026-04-16 |
| Finance Agent v2 | Finance | 4 | 51.509% | 2026-05-28 |
| Finance Agent v2 | Finance | 3 | 51.5% | 2026-05-28 |
| MortgageTax | Finance | 1 | 70.27% | 2026-05-28 |
| Rogo Big Finance Bench | Finance | 1 | 59% rubric / 41% final | 2026-05-28 |
| TaxBench | Finance | 10 | 14.37% mean pass^5 | 2026-05-27 |
| TaxEval v2 | Finance | 9 | 75.266% | 2026-05-28 |
| React Native Evals | Frontend Development | 7 | 82.7839% overall | 2026-05-28 |
| InfiniteBM Chess | Game | 1 | 1997.52 Elo / 16 games | 2026-05-28 |
| InfiniteBM Coup | Game | 4 | 1470.55 Elo / 47 games | 2026-05-28 |
| InfiniteBM Coup | Game | 5 | 1435.16 Elo / 16 games | 2026-05-28 |
| InfiniteBM Heads-Up No-Limit Hold'em | Game | 5 | 1401.16 Elo / 23 games | 2026-05-28 |
| InfiniteBM Heads-Up No-Limit Hold'em | Game | 23 | 1092.51 Elo / 115 games | 2026-05-28 |
| InfiniteBM Liar's Dice | Game | 7 | 1341.37 Elo / 116 games | 2026-05-28 |
| InfiniteBM Liar's Dice | Game | 13 | 1276.3 Elo / 39 games | 2026-05-28 |
| InfiniteBM Settlers of Catan | Game | 3 | 1740.25 Elo / 24 games | 2026-05-28 |
| InfiniteBM Werewolf | Game | 3 | 1255.77 Elo / 22 games | 2026-05-28 |
| InfiniteBM Werewolf | Game | 7 | 1123.57 Elo / 19 games | 2026-05-28 |
| BenchLM | General Knowledge | 5 | 90 | 2026-05-06 |
| GDPval | Generalization | 5 | 80.3% | 2026-04-23 |
| LMArena Text Arena | Generalization | 6 | 1477.55 | 2026-05-06 |
| HealthBench Professional | Healthcare | 2 | 51.9% | 2026-05-28 |
| MedCode | Healthcare | 4 | 54.858% | 2026-05-28 |
| MedScribe | Healthcare | 15 | 82.953% | 2026-05-28 |
| PhysicianBench | Healthcare | 3 | 29.3 +/- 2.5 | 2026-05-27 |
| HUMAINE | Human Preference | 10 | 3.68 | 2026-05-06 |
| AIIQ Composite IQ | Intelligence | 4 | 132 | 2026-05-12 |
| Artificial Analysis Intelligence Index | Intelligence | 3 | 57.28 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 13 | 51.82 | 2026-05-11 |
| GPQA Diamond | Intelligence | 10 | 90.152% | 2026-05-28 |
| Humanity's Last Exam | Intelligence | 2 | 54.7% | 2026-05-28 |
| Humanity's Last Exam | Intelligence | 8 | 39.6% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 22 | 31.2% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 3 | 54.7% | 2026-04-23 |
| Humanity's Last Exam | Intelligence | 3 | 54.7% | 2026-04-16 |
| MMLU Pro | Intelligence | 3 | 89.871% | 2026-05-28 |
| MMMU Pro | Intelligence | 11 | 85.549% | 2026-05-28 |
| Vals Index | Intelligence | 3 | 66.099% | 2026-05-28 |
| Vals Multimodal Index | Intelligence | 3 | 67.361% | 2026-05-28 |
| CaseLaw v2 | Legal | 5 | 68.381% | 2026-05-04 |
| Harvey Legal Agent Benchmark | Legal | 1 | 7.1% | 2026-05-28 |
| LegalBench | Legal | 9 | 85.251% | 2026-05-28 |
| Realm Warren | Legal | 1 | 0.36 | 2026-05-07 |
| Graphwalks BFS 1M F1 | Long Context | 3 | 40.3% | 2026-05-28 |
| Graphwalks BFS 256k F1 | Long Context | 2 | 76.9% | 2026-05-28 |
| Graphwalks BFS 256k F1 | Long Context | 1 | 76.9% | 2026-04-23 |
| Graphwalks Parents 1M F1 | Long Context | 3 | 56.6% | 2026-05-28 |
| Graphwalks Parents 256k F1 | Long Context | 3 | 93.6% | 2026-05-28 |
| Graphwalks Parents 256k F1 | Long Context | 1 | 93.6% | 2026-04-23 |
| OpenAI MRCR v2 8-needle 128K-256K | Long Context | 3 | 59.2% | 2026-04-23 |
| OpenAI MRCR v2 8-needle 512K-1M | Long Context | 3 | 32.2% | 2026-04-23 |
| AIME | Math | 7 | 96.25% | 2026-04-16 |
| ProofBench | Math | 4 | 54% | 2026-05-28 |
| FrontierMath 2025-02-28 Private | Mathematics | 5 | 43.8% | 2026-04-23 |
| FrontierMath Tier 4 2025-07-01 Private | Mathematics | 5 | 22.9% | 2026-04-23 |
| USAMO 2026 | Mathematics | 2 | 69.3% | 2026-05-28 |
| Global MMLU | Multilingual | 4 | 89.9% | 2026-05-28 |
| MMMLU | Multilingual | 2 | 91.5% | 2026-04-16 |
| Blueprint-Bench 2 | Multimodal | 6 | 0.652 +/- 0.009 | 2026-05-28 |
| ChartMuseum | Multimodal | 2 | 85.9% | 2026-05-28 |
| ChartQAPro | Multimodal | 2 | 69.8% | 2026-05-28 |
| CharXiv-R | Multimodal | 1 | 90.1% | 2026-05-28 |
| CharXiv-R | Multimodal | 2 | 0.91 | 2026-05-06 |
| CharXiv-R | Multimodal | 2 | 91% | 2026-04-16 |
| Design Arena | Multimodal | 6 | 1338 | 2026-05-06 |
| FigQA | Multimodal | 2 | 85.4% | 2026-05-28 |
| LMArena Vision Arena | Multimodal | 3 | 1314.23 | 2026-05-06 |
| CAIS Text Capabilities Index | Reasoning | 5 | 46.9 | 2026-05-27 |
| Context Arena | Reasoning | 48 | 28.81 | 2026-05-06 |
| Context Arena | Reasoning | 50 | 28.63 | 2026-05-06 |
| Context Arena | Reasoning | 51 | 28.54 | 2026-05-06 |
| Context Arena | Reasoning | 52 | 27.96 | 2026-05-06 |
| Context Arena | Reasoning | 67 | 15.12 | 2026-05-06 |
| GPQA Diamond | Reasoning | 2 | 94.2% | 2026-05-28 |
| GPQA Diamond | Reasoning | 7 | 91.4% | 2026-05-11 |
| GPQA Diamond | Reasoning | 23 | 88.5% | 2026-05-11 |
| GPQA Diamond | Reasoning | 3 | 94.2% | 2026-04-23 |
| GPQA Diamond | Reasoning | 4 | 94.2% | 2026-04-16 |
| CAIS Risk Index | Safety | 1 | 32.9 | 2026-05-27 |
| BioMysteryBench Human-Difficult | Science | 3 | 24.7% | 2026-05-28 |
| BioMysteryBench Human-Difficult | Science | 2 | 27.0% | 2026-04-29 |
| BioMysteryBench Human-Solvable | Science | 3 | 78.9% | 2026-05-28 |
| BioMysteryBench Human-Solvable | Science | 2 | 78.9% | 2026-04-29 |
| CritPt | Science | 12 | 12% | 2026-05-11 |
| CritPt | Science | 32 | 5.1% | 2026-05-11 |
| DeepSearchQA | Search | 3 | 89.4% | 2026-05-28 |
| ProgramBench | Software Engineering | 1 | 0% | 2026-05-05 |
| ProgramBench (Anthropic Harness) | Software Engineering | 2 | 84% | 2026-05-28 |
| SWE-bench Multilingual | Software Engineering | 2 | 80.5% | 2026-05-28 |
| SWE-bench Multimodal | Software Engineering | 2 | 34.5% | 2026-05-28 |
| SWE-bench Pro | Software Engineering | 2 | 64.3% | 2026-05-28 |
| SWE-bench Pro | Software Engineering | 1 | 64.3% | 2026-04-23 |
| SWE-bench Pro | Software Engineering | 2 | 64.3% | 2026-04-16 |
| SWE-bench Verified | Software Engineering | 2 | 87.6% | 2026-05-28 |
| SWE-bench Verified | Software Engineering | 2 | 87.6% | 2026-04-16 |
| Structured Output Benchmark | Structured Output | 4 | 86.40 | 2026-05-06 |
| CAIS Vision Capabilities Index | Vision | 15 | 50.1 | 2026-05-27 |
No matching rows.