Anthropic · model
Claude Sonnet 5 benchmark scores
As of 2026-11-22, Claude Sonnet 5 (Anthropic) has measured scores on 53 benchmarks and estimated scores on 146 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 91.1% | measured |
| AA-HLE | 41.3% | measured |
| AA-SciCode | 54.3% | measured |
| AIME26 | 99.2% | estimated ± 1.2 pp, medium confidence |
| Artificial Analysis Intelligence Index | 38.2% | measured |
| CritPt | 16.9% | measured |
| GDPval-AA | 48.2% | measured |
| GPQA Diamond | 90.3% | estimated ± 1.8 pp, high confidence |
| HLE | 57.4% | measured |
| AA-LCR | 82.0% | measured |
| LiveCodeBench v6 | 87.5% | estimated ± 2.2 pp, medium confidence |
| AA-Omniscience Accuracy | 40.1% | measured |
| SciCode | 41.5% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 80.4% | measured |
| BrowseComp | 84.7% | measured |
| HLE w/ tools | 57.4% | measured |
| LongBench v2 | 67.4% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 46.1% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 98.1% | estimated ± 3.1 pp, high confidence |
| AA Coding Index | 71.6% | measured |
| AA-MMMU-Pro | 77.3% | measured |
| APEX-Agents | 40.8% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 38.0% | estimated ± 3.5 pp, low confidence |
| BioMysteryBench (human-difficult) | 47.2% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 92.5% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 85.2% | measured |
| AutomationBench | 23.5% | estimated ± 7.1 pp, low confidence |
| BFCL v4 | 76.5% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 79.5% | estimated ± 3.1 pp, low confidence |
| JobBench | 51.1% | estimated ± 8.7 pp, medium confidence |
| SkillsBench | 56.7% | estimated ± 4.1 pp, medium confidence |
| SWE-bench Pro | 63.2% | measured |
| WideResearch | 81.4% | estimated ± 2.1 pp, medium confidence |
| AA Agentic Index | 44.3% | measured |
| MMLU-Pro | 85.7% | estimated ± 2.5 pp, low confidence |
| FailureSensorIQ | 66.9% | estimated ± 1.7 pp, high confidence |
| GPQA | 92.2% | estimated ± 1.9 pp, high confidence |
| MMLU | 90.5% | estimated ± 0.9 pp, medium confidence |
| Vals GPQA Diamond | 88.9% | measured |
| Vals LiveCodeBench | 82.4% | measured |
| Vals MMLU-Pro | 87.5% | measured |
| MMMLU | 90.5% | estimated ± 0.7 pp, low confidence |
| MMMU | 84.8% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 45.0% | measured |
| AA MMLU-Pro | 87.4% | estimated ± 0.7 pp, high confidence |
| Gert Labs | 47.0% | measured |
| AA-AnalystAgent | 46.3% | measured |
| AA EnterpriseOps-Gym | 44.7% | measured |
| AA Harvey LAB v1.0 | 92.9% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 37.3% | measured |
| AA Terminal-Bench 2.1 | 80.5% | measured |
| ApprenticeBench | 16.0% | measured |
| ARC-AGI-1 | 95.7% | estimated ± 0.8 pp, low confidence |
| ARC-AGI-2 | 73.6% | estimated ± 13.0 pp, low confidence |
| BabaIsBench | 67.0% | measured |
| CursorBench 3.1 | 54.6% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 61.5% | measured |
| EBR-bench | 25.6% | estimated ± 10.4 pp, low confidence |
| Terminal-Bench 3.0 | 14.6% | measured |
| FrontierCode 1.1 Main | 42.7% | measured |
| FrontierMath v2 (Tier 4) | 29.3% | measured |
| FrontierMath v2 (Tiers 1-3) | 65.6% | measured |
| FrontierSWE v2 | 13.6% | estimated ± 5.8 pp, low confidence |
| Furniture Assembly | 42.0% | estimated ± 7.1 pp, medium confidence |
| MaxxBench | 53.8% | estimated ± 5.6 pp, medium confidence |
| MazeBench | 0.0% | measured |
| MirrorCode | 63.3% | measured |
| Mystery Game Puzzles | 35.0% | measured |
| NYT Connections | 75.1% | measured |
| OfficeQA Pro | 65.8% | estimated ± 2.5 pp, low confidence |
| OSWorld-Verified | 81.2% | measured |
| ParseBench-1 | 61.2% | measured |
| Terminal-Bench 4.1 | 12.1% | measured |
| Terminal-Bench Hard | 55.8% | estimated ± 2.8 pp, medium confidence |
| Vals SWE-bench | 79.6% | measured |
| Terminal-Bench 2.1 (Vals AI) | 74.5% | measured |
| VulcanBench v3 | 82.1% | estimated ± 5.1 pp, low confidence |
| CWE-Bench-AA | 57.8% | estimated ± 5.2 pp, medium confidence |
| AA Cyber Index | 26.5% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 16.0% | estimated ± 8.2 pp, medium confidence |
| Harvey LAB-AA v1.1 | 7.4% | estimated ± 4.0 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 57.5% | estimated ± 4.3 pp, medium confidence |
| HealthBench Professional (raw, Artificial Analysis) | 63.3% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 43.9% | estimated ± 3.2 pp, high confidence |
| Bug Hunt Bench | 22.8% | estimated ± 7.9 pp, low confidence |
| Chartography (tools) | 81.7% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 34.1% | measured |
| CWE-bench v1 | 57.4% | estimated ± 5.1 pp, medium confidence |
| DeepSWE | 65.9% | estimated ± 4.1 pp, low confidence |
| DRACO | 86.9% | estimated ± 0.7 pp, low confidence |
| FrontierCode 2.0 | 27.1% | estimated ± 4.7 pp, medium confidence |
| FrontierPhysics | 1.7% | estimated ± 4.6 pp, high confidence |
| HLE w/o tools | 43.2% | measured |
| OSWorld 2.0 | 15.9% | estimated ± 3.6 pp, high confidence |
| OSWorld 2.1 | 57.0% | measured |
| OSWorld 2.1 Offline | 54.4% | estimated ± 1.9 pp, medium confidence |
| PostTrainBench v1.1 | 35.6% | estimated ± 1.7 pp, low confidence |
| ProgramBench | 78.3% | estimated ± 6.0 pp, low confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, medium confidence |
| StealthMark | 41.0% | estimated ± 3.5 pp, high confidence |
| SWE Multilingual | 78.3% | measured |
| SWE-bench Multimodal | 28.1% | measured |
| Terminal-Bench 4.0 | 19.7% | estimated ± 4.5 pp, high confidence |
| Terminal-Bench-Science 0.1 | 0.0% | estimated ± 10.7 pp, low confidence |
| Toolathlon-Verified | 70.9% | estimated ± 2.3 pp, medium confidence |
| VulcanBench Frontier v4 | 82.0% | estimated ± 1.8 pp, medium confidence |
| AA AutomationBench | 42.0% | estimated ± 7.9 pp, low confidence |
| GDP.pdf | 19.0% | estimated ± 4.2 pp, high confidence |
| AA Terminal-Bench 4.0 | 11.7% | estimated ± 6.2 pp, medium confidence |
| ARC-AGI-3 | 5.0% | estimated ± 7.2 pp, medium confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, medium confidence |
| cursorBench41 | 35.7% | estimated ± 2.0 pp, medium confidence |
| CWE-bench | 57.5% | estimated ± 4.6 pp, high confidence |
| MKA | 34.9% | estimated ± 4.6 pp, high confidence |
| SkillsBench official leaderboard (BenchFlow) | 55.1% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 35.8% | estimated ± 12.1 pp, low confidence |
| CompileBench | 100.0% | estimated ± 10.0 pp, low confidence |
| OTelBench | 22.5% | estimated ± 6.6 pp, medium confidence |
| Vibe Code Bench | 71.8% | estimated ± 5.6 pp, low confidence |
| FACTS Multimodal | 42.5% | estimated ± 4.0 pp, high confidence |
| Hermes Bench | 71.2% | estimated ± 1.8 pp, high confidence |
| Hermes Index | 37.2% | estimated ± 3.1 pp, high confidence |
| ParseBench-2 | 66.8% | estimated ± 3.5 pp, high confidence |
| CharXiv | 88.3% | measured |
| CharXiv w/o tools | 77.0% | measured |
| ExploitBench | 37.6% | estimated ± 1.9 pp, medium confidence |
| ExploitGym | 12.2% | estimated ± 2.7 pp, high confidence |
| AI2D_TEST | 93.5% | estimated ± 0.9 pp, low confidence |
| C-Eval | 97.0% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 69.8% | estimated ± 6.2 pp, low confidence |
| CountBench | 96.5% | estimated ± 2.9 pp, medium confidence |
| DynaMath | 87.7% | estimated ± 0.8 pp, low confidence |
| ERQA | 58.0% | estimated ± 2.9 pp, medium confidence |
| HMMT Feb 2026 | 94.5% | estimated ± 1.5 pp, medium confidence |
| HMMT Nov 2025 | 95.3% | estimated ± 1.5 pp, low confidence |
| INCLUDE | 86.0% | estimated ± 2.0 pp, medium confidence |
| MathVision | 87.9% | estimated ± 3.1 pp, high confidence |
| MCP Atlas | 77.7% | estimated ± 5.8 pp, low confidence |
| MLVU (M-Avg) | 88.4% | estimated ± 1.5 pp, high confidence |
| MMAnswerBench | 90.5% | estimated ± 2.4 pp, low confidence |
| MMLU-ProX | 86.0% | estimated ± 1.3 pp, high confidence |
| MMLU-Redux | 96.0% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 78.3% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 45.2% | estimated ± 4.7 pp, high confidence |
| PostTrainBench v1 | 23.9% | estimated ± 3.6 pp, high confidence |
| QwenClawBench | 93.2% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 86.7% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 83.2% | estimated ± 6.8 pp, medium confidence |
| SuperGPQA | 96.2% | estimated ± 7.2 pp, low confidence |
| Terminal-Bench 2.0 | 75.8% | estimated ± 5.8 pp, medium confidence |
| Toolathlon | 54.9% | estimated ± 1.7 pp, medium confidence |
| V* | 100.0% | estimated ± 7.5 pp, medium confidence |
| Video-MME (w/o subtitle) | 84.7% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 90.1% | estimated ± 2.9 pp, high confidence |
| VideoMMMU | 86.8% | estimated ± 1.5 pp, medium confidence |
| We-Math | 84.6% | estimated ± 7.9 pp, low confidence |
| AA LiveCodeBench | 91.4% | estimated ± 2.6 pp, medium confidence |
| HealthBench Hard | 31.8% | estimated ± 8.6 pp, low confidence |
| LiveCodeBench Pro | 86.2% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 78.4% | estimated ± 6.4 pp, low confidence |
| MedXpertQA (Text) | 60.7% | estimated ± 8.9 pp, low confidence |
| React Native Evals | 82.0% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 20.7% | estimated ± 1.9 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, low confidence |
| PostTrainBench | 21.4% | estimated ± 3.7 pp, high confidence |
| DAYJOB | 1.7% | measured |
| DAYJOB Healthcare | 0.0% | measured |
| Finance Agent v2 | 55.6% | estimated ± 2.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 88.4% | estimated ± 0.6 pp, medium confidence |
| FrontierCode 1.1 Extended | 55.1% | estimated ± 1.6 pp, medium confidence |
| HealthBench (raw) | 49.9% | estimated ± 6.0 pp, medium confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.4 pp, medium confidence |
| HealthBench Professional | 52.4% | estimated ± 4.2 pp, medium confidence |
| HealthBench Professional (raw) | 60.4% | estimated ± 4.5 pp, high confidence |
| HLE-Verified | 31.0% | measured |
| LABBench2 | 80.1% | measured |
| ScarfBench | 45.6% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 72.1% | estimated ± 2.8 pp, medium confidence |
| Cookie-Bench | 81.5% | estimated ± 1.3 pp, medium confidence |
| STEMBench | 2.5% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 45.7% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 82.3% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 30.9% | estimated ± 9.7 pp, medium confidence |
| BabyVision w/ Python | 85.0% | estimated ± 3.7 pp, low confidence |
| OpenHarmony Bench v1.0 | 58.9% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 46.4% | estimated ± 5.8 pp, medium confidence |
| BabyVision | 42.3% | estimated ± 7.4 pp, low confidence |
| MMVU | 79.9% | estimated ± 3.6 pp, medium confidence |
| PerceptionBench | 55.3% | estimated ± 3.8 pp, low confidence |
| ZeroBench | 14.7% | estimated ± 7.1 pp, low confidence |
| MRCRv2 | 85.9% | estimated ± 11.3 pp, low confidence |
| LVBench | 62.8% | estimated ± 8.2 pp, low confidence |
| MMLongBench-Doc | 61.5% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 34.0% | estimated ± 2.8 pp, medium confidence |
| LifeVal | 75.9% | estimated ± 1.6 pp, medium confidence |
| MMMU-Pro w/ Python | 80.3% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.9% | estimated ± 1.4 pp, medium confidence |
| MathVision w/ Python | 94.8% | estimated ± 1.0 pp, low confidence |
| PinchBench | 90.4% | estimated ± 3.6 pp, low confidence |