Anthropic · model
Claude Opus 4.8 benchmark scores
As of 2026-10-07, Claude Opus 4.8 (Anthropic) has measured scores on 47 benchmarks and estimated scores on 81 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 92.0% | measured |
| AA-HLE | 48.7% | measured |
| AA-SciCode | 54.4% | measured |
| AIME26 | 100.0% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 41.8% | measured |
| CritPt | 20.9% | measured |
| GDPval-AA | 47.8% | measured |
| GPQA Diamond | 93.6% | measured |
| HLE | 57.9% | measured |
| IFBench | 62.6% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 77.7% | measured |
| LiveCodeBench v6 | 92.2% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 48.8% | measured |
| SciCode | 52.3% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 74.6% | measured |
| BrowseComp | 84.3% | measured |
| HLE w/ tools | 57.5% | estimated ± 4.6 pp, high confidence |
| IFEval | 92.9% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 49.0% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 94.4% | measured |
| AA Coding Index | 74.3% | measured |
| AA-MMMU-Pro | 83.7% | estimated ± 2.9 pp, high confidence |
| APEX-Agents | 35.6% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 36.5% | estimated ± 2.9 pp, medium confidence |
| BioMysteryBench (human-difficult) | 45.1% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 93.1% | measured |
| SWE-bench Verified | 88.6% | measured |
| AutomationBench | 28.6% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 77.3% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 79.6% | estimated ± 4.6 pp, high confidence |
| JobBench | 53.4% | estimated ± 4.9 pp, medium confidence |
| SWE-bench Pro | 69.2% | measured |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 79.7% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 42.6% | measured |
| MMLU-Pro | 85.8% | estimated ± 2.5 pp, low confidence |
| FrontierMath v2 (Tier 4) | 31.3% | measured |
| FrontierMath v2 (Tiers 1-3) | 47.2% | measured |
| GPQA | 93.6% | measured |
| AA-IFBench | 62.2% | measured |
| Gert Labs | 73.0% | measured |
| AA-AnalystAgent | 54.1% | estimated ± 5.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 45.5% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 92.7% | estimated ± 1.2 pp, medium confidence |
| ApprenticeBench | 20.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 92.5% | measured |
| ARC-AGI-2 | 72.1% | measured |
| CursorBench 3.1 | 58.4% | measured |
| CursorBench 3.2 | 62.3% | measured |
| Terminal-Bench 3.0 | 21.1% | measured |
| FrontierCode 1.1 Main | 46.5% | measured |
| FrontierSWE v2 | 31.5% | estimated ± 9.0 pp, medium confidence |
| OfficeQA Pro | 66.2% | measured |
| OSWorld-Verified | 83.4% | measured |
| Vals GPQA Diamond | 92.4% | measured |
| Vals LiveCodeBench | 87.8% | measured |
| Vals MMLU-Pro | 89.6% | measured |
| Vals SWE-bench | 88.6% | measured |
| Terminal-Bench 2.1 (Vals AI) | 71.9% | measured |
| VulcanBench v3 | 82.7% | estimated ± 5.1 pp, low confidence |
| AA AutomationBench | 24.8% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 20.6% | estimated ± 4.9 pp, high confidence |
| AA ITBench | 49.9% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 47.4% | estimated ± 5.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 82.5% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 12.2% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 38.2% | estimated ± 1.6 pp, high confidence |
| CWE-bench v1 | 54.3% | estimated ± 6.9 pp, medium confidence |
| DeepSWE | 69.4% | estimated ± 3.4 pp, medium confidence |
| HLE w/o tools | 49.8% | measured |
| OSWorld 2.0 | 20.6% | measured |
| PostTrainBench v1.1 | 32.9% | measured |
| ProgramBench | 87.9% | estimated ± 4.8 pp, medium confidence |
| SWE Multilingual | 84.4% | measured |
| Toolathlon-Verified | 73.4% | estimated ± 1.0 pp, medium confidence |
| Vibe Code Bench | 75.2% | estimated ± 5.6 pp, low confidence |
| CharXiv | 89.9% | measured |
| CharXiv w/o tools | 80.5% | measured |
| ExploitGym | 13.3% | estimated ± 6.1 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 75.0% | estimated ± 3.2 pp, medium confidence |
| DeepPlanning | 51.1% | estimated ± 13.1 pp, low confidence |
| HMMT Nov 2025 | 93.2% | estimated ± 2.6 pp, low confidence |
| MathVision | 86.0% | estimated ± 2.1 pp, low confidence |
| MCP Atlas | 82.2% | measured |
| MCP-Tasks | 77.1% | estimated ± 0.6 pp, low confidence |
| MMAnswerBench | 89.0% | estimated ± 1.3 pp, low confidence |
| MMLU-ProX | 88.3% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 97.3% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 74.4% | estimated ± 1.4 pp, medium confidence |
| NL2Repo | 52.5% | estimated ± 4.7 pp, high confidence |
| NOVA-63 | 61.0% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 67.7% | estimated ± 2.6 pp, medium confidence |
| ScreenSpot Pro | 87.9% | measured |
| SuperGPQA | 85.2% | estimated ± 7.5 pp, low confidence |
| Terminal-Bench 2.0 | 74.8% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 59.9% | measured |
| VideoMMMU | 87.1% | estimated ± 1.5 pp, high confidence |
| ERQA | 71.2% | estimated ± 3.7 pp, high confidence |
| HealthBench Hard | 36.1% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 90.4% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 79.0% | estimated ± 6.4 pp, low confidence |
| MedXpertQA (Text) | 66.3% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 88.1% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 97.0% | estimated ± 2.4 pp, low confidence |
| ResearchClawBench | 21.1% | measured |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 1.5% | measured |
| FrontierMath (legacy) | 47.7% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 89.2% | estimated ± 0.6 pp, medium confidence |
| DRACO | 81.2% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 55.2% | estimated ± 1.6 pp, medium confidence |
| HealthBench (raw) | 56.7% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.8% | estimated ± 0.9 pp, medium confidence |
| HealthBench Professional | 59.9% | estimated ± 1.3 pp, medium confidence |
| HealthBench Professional (raw) | 66.6% | estimated ± 5.0 pp, medium confidence |
| HLE-Verified | 35.3% | estimated ± 0.7 pp, low confidence |
| LABBench2 | 75.9% | estimated ± 1.3 pp, low confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, high confidence |
| SimpleVQA | 65.6% | estimated ± 5.7 pp, low confidence |
| MMMLU | 90.9% | estimated ± 1.1 pp, low confidence |
| MMLU | 94.8% | estimated ± 1.1 pp, low confidence |
| MathVision w/ Python | 93.3% | estimated ± 0.9 pp, low confidence |
| RealWorldQA | 87.3% | estimated ± 1.1 pp, medium confidence |
| Video-MME (with subtitle) | 89.4% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 90.8% | estimated ± 7.4 pp, low confidence |