Anthropic · model
Claude Opus 4.7 benchmark scores
As of 2026-10-07, Claude Opus 4.7 (Anthropic) has measured scores on 24 benchmarks and estimated scores on 86 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 88.5% | measured |
| AA-HLE | 33.3% | measured |
| AA-SciCode | 55.8% | estimated ± 3.5 pp, high confidence |
| AIME26 | 100.0% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 30.9% | measured |
| CritPt | 5.1% | measured |
| GDPval-AA | 43.3% | estimated ± 7.5 pp, medium confidence |
| GPQA Diamond | 90.8% | estimated ± 1.7 pp, high confidence |
| HLE | 37.5% | estimated ± 9.5 pp, medium confidence |
| IFBench | 56.3% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 75.7% | measured |
| AA-Omniscience Accuracy | 44.7% | measured |
| SciCode | 46.9% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 83.3% | estimated ± 6.9 pp, medium confidence |
| BrowseComp | 82.8% | estimated ± 2.2 pp, high confidence |
| IFEval | 89.8% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| τ²-bench results | 74.0% | measured |
| AA Coding Index | 73.5% | estimated ± 3.1 pp, high confidence |
| AA-MMMU-Pro | 76.4% | measured |
| APEX-Agents-AA | 35.1% | estimated ± 2.9 pp, medium confidence |
| BioMysteryBench (human-difficult) | 43.3% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 77.2% | estimated ± 7.5 pp, low confidence |
| SWE-bench Verified | 83.1% | estimated ± 0.8 pp, medium confidence |
| BFCL v4 | 52.7% | estimated ± 9.8 pp, low confidence |
| CyberGym | 72.5% | estimated ± 5.0 pp, medium confidence |
| JobBench | 47.3% | estimated ± 4.9 pp, medium confidence |
| SWE-bench Pro | 57.2% | estimated ± 2.1 pp, high confidence |
| τ³-bench results | 68.9% | estimated ± 8.9 pp, low confidence |
| WideResearch | 79.4% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 28.7% | estimated ± 6.4 pp, medium confidence |
| MMLU-Pro | 85.7% | estimated ± 3.5 pp, high confidence |
| FrontierMath v2 (Tier 4) | 22.9% | measured |
| FrontierMath v2 (Tiers 1-3) | 43.8% | measured |
| GPQA | 93.5% | estimated ± 1.6 pp, medium confidence |
| AA-IFBench | 43.6% | measured |
| Gert Labs | 65.6% | measured |
| AA-AnalystAgent | 51.4% | estimated ± 5.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 15.6% | estimated ± 3.6 pp, low confidence |
| AA Harvey LAB | 89.3% | estimated ± 1.3 pp, medium confidence |
| ApprenticeBench | 7.0% | measured |
| ARC-AGI-1 | 87.4% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 61.8% | estimated ± 12.6 pp, low confidence |
| CursorBench 3.1 | 56.2% | estimated ± 5.8 pp, low confidence |
| CursorBench 3.2 | 55.6% | estimated ± 1.6 pp, low confidence |
| Terminal-Bench 3.0 | 11.9% | estimated ± 6.9 pp, medium confidence |
| FrontierCode 1.1 Main | 38.5% | measured |
| FrontierSWE v2 | 11.6% | estimated ± 9.5 pp, medium confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 74.2% | estimated ± 1.9 pp, medium confidence |
| Vals GPQA Diamond | 90.2% | measured |
| Vals LiveCodeBench | 85.1% | measured |
| Vals MMLU-Pro | 89.9% | measured |
| Vals SWE-bench | 82.0% | measured |
| Terminal-Bench 2.1 (Vals AI) | 68.5% | measured |
| VulcanBench v3 | 83.7% | estimated ± 5.6 pp, low confidence |
| AA AutomationBench | 41.7% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 22.0% | estimated ± 4.4 pp, low confidence |
| AA ITBench | 65.8% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 31.0% | estimated ± 14.6 pp, low confidence |
| AA Terminal-Bench 2.1 | 83.8% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 23.3% | estimated ± 14.0 pp, low confidence |
| CursorBench 4.0 | 32.5% | estimated ± 4.4 pp, medium confidence |
| DeepSWE | 58.9% | estimated ± 3.4 pp, low confidence |
| HLE w/o tools | 51.3% | estimated ± 5.1 pp, medium confidence |
| OSWorld 2.0 | 13.9% | measured |
| PostTrainBench v1.1 | 28.6% | measured |
| ProgramBench | 0.5% | estimated ± 4.8 pp, low confidence |
| Toolathlon-Verified | 69.6% | estimated ± 1.0 pp, low confidence |
| Vibe Code Bench | 71.0% | measured |
| CharXiv | 83.8% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 80.5% | estimated ± 2.4 pp, high confidence |
| ExploitGym | 3.5% | estimated ± 6.9 pp, low confidence |
| C-Eval | 94.3% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 73.3% | estimated ± 3.2 pp, medium confidence |
| HMMT Nov 2025 | 93.2% | estimated ± 2.6 pp, low confidence |
| MathVision | 89.1% | estimated ± 4.9 pp, high confidence |
| MCP Atlas | 79.6% | estimated ± 10.4 pp, low confidence |
| MCP-Tasks | 79.7% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 87.1% | estimated ± 1.3 pp, low confidence |
| MMLU-Redux | 97.0% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 77.6% | estimated ± 4.4 pp, medium confidence |
| NL2Repo | 47.2% | estimated ± 4.7 pp, high confidence |
| ScreenSpot Pro | 75.2% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 83.5% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.0 | 72.5% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 53.0% | estimated ± 1.7 pp, medium confidence |
| ERQA | 65.9% | estimated ± 3.9 pp, high confidence |
| HealthBench Hard | 27.8% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 74.3% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 96.3% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 82.8% | measured |
| ResearchClawBench | 20.7% | measured |
| SWE-Rebench | 62.2% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, high confidence |
| FrontierMath (legacy) | 44.3% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 33.8% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 42.6% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 59.9% | estimated ± 1.3 pp, medium confidence |
| HealthBench Professional (raw) | 53.4% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.5% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 83.0% | estimated ± 1.8 pp, low confidence |
| MMMU | 84.2% | estimated ± 0.9 pp, high confidence |
| OpenHarmony Bench | 54.9% | estimated ± 3.2 pp, high confidence |
| MMLU | 94.2% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 79.5% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 85.7% | estimated ± 1.2 pp, medium confidence |
| OmniDocBench 1.5 | 91.7% | estimated ± 6.4 pp, low confidence |