Anthropic · model
Claude Sonnet 4.6 benchmark scores
As of 2026-11-22, Claude Sonnet 4.6 (Anthropic) has measured scores on 40 benchmarks and estimated scores on 130 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 79.9% | measured |
| AA-HLE | 13.3% | measured |
| AA-SciCode | 52.2% | estimated ± 1.7 pp, medium confidence |
| Artificial Analysis Intelligence Index | 24.7% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 34.5% | estimated ± 5.0 pp, high confidence |
| GPQA Diamond | 89.9% | estimated ± 0.1 pp, high confidence |
| HLE | 49.0% | measured |
| IFBench | 54.3% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 68.3% | measured |
| LiveCodeBench v6 | 87.4% | estimated ± 2.2 pp, medium confidence |
| AA-Omniscience Accuracy | 38.6% | measured |
| SciCode | 40.9% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 74.8% | estimated ± 6.7 pp, medium confidence |
| BrowseComp | 82.9% | estimated ± 1.9 pp, high confidence |
| HLE w/ tools | 50.0% | estimated ± 4.9 pp, medium confidence |
| IFEval | 89.2% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 57.6% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 44.9% | estimated ± 10.7 pp, low confidence |
| τ²-bench results | 79.5% | measured |
| AA Coding Index | 66.0% | estimated ± 3.6 pp, medium confidence |
| AA-MMMU-Pro | 70.6% | measured |
| APEX-Agents-AA | 32.4% | estimated ± 2.9 pp, medium confidence |
| BioMysteryBench (human-difficult) | 15.7% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 73.4% | estimated ± 7.5 pp, low confidence |
| SWE-bench Verified | 79.6% | measured |
| AutomationBench | 18.0% | estimated ± 10.4 pp, low confidence |
| BFCL v4 | 61.1% | estimated ± 8.5 pp, low confidence |
| CyberGym | 65.2% | measured |
| JobBench | 36.9% | measured |
| SWE-bench Pro | 57.0% | estimated ± 2.9 pp, medium confidence |
| WideResearch | 78.4% | estimated ± 1.2 pp, medium confidence |
| AA Agentic Index | 28.7% | estimated ± 5.8 pp, medium confidence |
| MMLU-Pro | 79.2% | measured |
| AA-IFBench | 41.2% | measured |
| BBH | 95.4% | estimated ± 2.8 pp, medium confidence |
| FailureSensorIQ | 64.7% | estimated ± 1.7 pp, high confidence |
| GPQA | 89.9% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, medium confidence |
| Vals GPQA Diamond | 85.6% | measured |
| Vals LiveCodeBench | 82.1% | measured |
| Vals MMLU-Pro | 87.3% | measured |
| MMMLU | 86.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 80.5% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 23.0% | measured |
| AA MMLU-Pro | 87.1% | estimated ± 0.7 pp, high confidence |
| Gert Labs | 47.3% | measured |
| AA-AnalystAgent | 44.8% | estimated ± 5.9 pp, low confidence |
| AA EnterpriseOps-Gym | 45.0% | estimated ± 1.2 pp, medium confidence |
| AA Harvey LAB v1.0 | 88.9% | estimated ± 1.3 pp, medium confidence |
| AA Terminal-Bench 2.1 | 80.3% | estimated ± 2.5 pp, medium confidence |
| ApprenticeBench | 2.0% | measured |
| ARC-AGI-1 | 86.0% | measured |
| ARC-AGI-2 | 58.3% | measured |
| CursorBench 3.1 | 48.8% | measured |
| CursorBench 3.2 | 51.0% | estimated ± 5.0 pp, low confidence |
| EBR-bench | 9.4% | estimated ± 8.1 pp, low confidence |
| Terminal-Bench 3.0 | 4.4% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 24.3% | measured |
| FrontierSWE v2 | 9.0% | estimated ± 9.5 pp, low confidence |
| Furniture Assembly | 32.9% | estimated ± 9.3 pp, medium confidence |
| MaxxBench | 47.2% | estimated ± 8.8 pp, medium confidence |
| MazeBench | 0.0% | measured |
| Mystery Game Puzzles | 16.0% | measured |
| NYT Connections | 44.8% | measured |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 72.1% | measured |
| ParseBench-1 | 54.4% | estimated ± 6.2 pp, medium confidence |
| Terminal-Bench 4.1 | 10.5% | estimated ± 14.9 pp, low confidence |
| Terminal-Bench Hard | 46.8% | estimated ± 3.9 pp, high confidence |
| Vals SWE-bench | 77.4% | measured |
| Terminal-Bench 2.1 (Vals AI) | 57.3% | measured |
| VulcanBench v3 | 81.9% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 43.3% | estimated ± 4.5 pp, medium confidence |
| AA Cyber Index | 39.4% | estimated ± 12.4 pp, low confidence |
| DeepsecBench-AA | 16.2% | estimated ± 8.2 pp, medium confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 53.3% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 59.1% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 31.9% | estimated ± 4.4 pp, low confidence |
| Chartography (tools) | 77.4% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 30.9% | estimated ± 3.4 pp, medium confidence |
| CWE-bench v1 | 57.4% | estimated ± 5.1 pp, medium confidence |
| DeepSWE | 56.3% | estimated ± 7.2 pp, low confidence |
| DRACO | 86.9% | estimated ± 0.7 pp, low confidence |
| FrontierPhysics | 2.5% | estimated ± 5.0 pp, low confidence |
| HLE w/o tools | 39.2% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 8.3% | measured |
| OSWorld 2.1 | 57.8% | estimated ± 3.6 pp, high confidence |
| OSWorld 2.1 Offline | 56.6% | estimated ± 10.1 pp, low confidence |
| PostTrainBench v1.1 | 21.9% | estimated ± 3.7 pp, medium confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, low confidence |
| StealthMark | 36.8% | estimated ± 9.2 pp, medium confidence |
| Toolathlon-Verified | 62.8% | estimated ± 1.0 pp, low confidence |
| AA AutomationBench | 52.7% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 16.4% | estimated ± 4.1 pp, medium confidence |
| AA Terminal-Bench 4.0 | 3.7% | estimated ± 13.7 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.3 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| CWE-bench | 45.3% | estimated ± 6.2 pp, medium confidence |
| MKA | 35.0% | estimated ± 4.6 pp, high confidence |
| SkillsBench official leaderboard (BenchFlow) | 47.2% | measured |
| BinaryAudit | 31.4% | estimated ± 12.0 pp, low confidence |
| CompileBench | 75.5% | estimated ± 10.0 pp, low confidence |
| OTelBench | 18.5% | estimated ± 4.1 pp, medium confidence |
| Vibe Code Bench | 51.5% | measured |
| FACTS Multimodal | 26.6% | estimated ± 4.0 pp, medium confidence |
| Hermes Index | 37.2% | estimated ± 3.1 pp, high confidence |
| ParseBench-2 | 58.7% | estimated ± 6.2 pp, medium confidence |
| CharXiv | 77.4% | measured |
| CharXiv w/o tools | 77.8% | estimated ± 2.4 pp, medium confidence |
| ExploitBench | 30.5% | estimated ± 7.2 pp, low confidence |
| ExploitGym | 11.9% | estimated ± 6.3 pp, medium confidence |
| AI2D_TEST | 90.8% | estimated ± 0.9 pp, medium confidence |
| C-Eval | 93.0% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 67.8% | measured |
| CountBench | 91.9% | estimated ± 2.9 pp, low confidence |
| DynaMath | 84.7% | estimated ± 0.8 pp, medium confidence |
| ERQA | 45.0% | estimated ± 3.1 pp, medium confidence |
| MathVision | 78.9% | estimated ± 3.1 pp, high confidence |
| MCP Atlas | 72.3% | estimated ± 5.8 pp, low confidence |
| MLVU (M-Avg) | 84.8% | estimated ± 1.5 pp, high confidence |
| MMLU-Redux | 89.9% | estimated ± 0.6 pp, high confidence |
| MMMU-Pro | 72.0% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 43.8% | estimated ± 4.7 pp, high confidence |
| PostTrainBench v1 | 20.0% | estimated ± 3.1 pp, medium confidence |
| RealWorldQA | 82.3% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 66.9% | estimated ± 6.8 pp, medium confidence |
| SuperGPQA | 95.0% | measured |
| Terminal-Bench 2.0 | 59.1% | measured |
| Toolathlon | 51.9% | estimated ± 1.7 pp, low confidence |
| V* | 58.0% | estimated ± 7.5 pp, low confidence |
| Video-MME (w/o subtitle) | 80.1% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 85.3% | estimated ± 2.9 pp, high confidence |
| VideoMMMU | 84.9% | estimated ± 1.5 pp, medium confidence |
| We-Math | 84.6% | estimated ± 7.9 pp, low confidence |
| AA LiveCodeBench | 90.2% | estimated ± 2.6 pp, medium confidence |
| HealthBench Hard | 1.7% | estimated ± 5.1 pp, low confidence |
| MedXpertQA (MM) | 74.0% | estimated ± 6.4 pp, low confidence |
| MMLU-Pro (Arcee) | 80.5% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 80.6% | measured |
| ResearchClawBench | 18.3% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 60.7% | measured |
| PostTrainBench | 19.4% | estimated ± 3.7 pp, medium confidence |
| DAYJOB | 1.3% | estimated ± 3.2 pp, high confidence |
| DAYJOB Healthcare | 0.7% | estimated ± 4.2 pp, high confidence |
| Finance Agent v2 | 55.6% | estimated ± 2.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 48.1% | estimated ± 7.6 pp, low confidence |
| HealthBench (length-adjusted) | 53.5% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 50.9% | estimated ± 4.2 pp, low confidence |
| HLE-Verified | 1.2% | estimated ± 4.6 pp, low confidence |
| LABBench2 | 81.6% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 48.3% | estimated ± 12.3 pp, low confidence |
| BlenderWorld (text-only) | 70.0% | estimated ± 2.8 pp, medium confidence |
| Cookie-Bench | 76.9% | estimated ± 1.3 pp, medium confidence |
| STEMBench | 2.5% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 43.7% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 79.0% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 22.5% | estimated ± 3.3 pp, low confidence |
| BabyVision w/ Python | 84.7% | estimated ± 4.0 pp, low confidence |
| OpenHarmony Bench v1.0 | 53.5% | estimated ± 3.2 pp, high confidence |
| SEC-Bench Pro | 39.8% | estimated ± 9.3 pp, medium confidence |
| BabyVision | 26.4% | estimated ± 11.5 pp, low confidence |
| MMVU | 75.0% | estimated ± 3.6 pp, medium confidence |
| MRCRv2 | 65.9% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.8% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 21.5% | estimated ± 2.2 pp, low confidence |
| LifeVal | 75.2% | estimated ± 3.8 pp, medium confidence |
| MMMU-Pro w/ Python | 74.3% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |