Anthropic · model
Claude Fable 5.1 benchmark scores
As of 2026-10-07, Claude Fable 5.1 (Anthropic) has measured scores on 41 benchmarks and estimated scores on 61 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 93.7% | measured |
| AA-HLE | 59.1% | measured |
| AA-SciCode | 63.1% | measured |
| Artificial Analysis Intelligence Index | 53.3% | measured |
| CritPt | 29.7% | measured |
| GDPval-AA | 62.9% | measured |
| GPQA Diamond | 94.7% | estimated ± 1.4 pp, high confidence |
| HLE | 65.0% | measured |
| AA-LCR | 85.3% | measured |
| LiveCodeBench v6 | 98.9% | estimated ± 2.1 pp, medium confidence |
| AA-Omniscience Accuracy | 67.2% | measured |
| SciCode | 57.8% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 89.5% | estimated ± 3.9 pp, medium confidence |
| BrowseComp | 84.5% | estimated ± 2.2 pp, high confidence |
| HLE w/ tools | 58.2% | estimated ± 4.6 pp, medium confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 85.4% | estimated ± 4.8 pp, medium confidence |
| AA Coding Index | 81.6% | measured |
| APEX-Agents | 49.1% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 38.2% | estimated ± 2.9 pp, medium confidence |
| BioMysteryBench (human-difficult) | 51.6% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 94.3% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 94.6% | estimated ± 2.5 pp, medium confidence |
| AutomationBench | 31.4% | measured |
| BFCL v4 | 78.3% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 80.0% | estimated ± 3.7 pp, high confidence |
| JobBench | 65.2% | estimated ± 3.4 pp, low confidence |
| SWE-bench Pro | 81.2% | measured |
| WideResearch | 85.6% | estimated ± 3.9 pp, low confidence |
| AA Agentic Index | 58.0% | measured |
| MMLU-Pro | 86.0% | estimated ± 2.5 pp, low confidence |
| GPQA | 95.9% | estimated ± 1.6 pp, medium confidence |
| Gert Labs | 100.0% | estimated ± 3.0 pp, low confidence |
| AA-AnalystAgent | 57.5% | measured |
| AA EnterpriseOps-Gym | 56.3% | estimated ± 1.8 pp, low confidence |
| AA Harvey LAB | 93.0% | measured |
| ApprenticeBench | 72.0% | measured |
| ARC-AGI-1 | 97.5% | measured |
| ARC-AGI-2 | 90.0% | measured |
| CursorBench 3.1 | 76.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 73.4% | measured |
| Terminal-Bench 3.0 | 34.5% | estimated ± 6.9 pp, medium confidence |
| FrontierCode 1.1 Main | 57.9% | estimated ± 1.6 pp, low confidence |
| FrontierSWE v2 | 56.3% | measured |
| OSWorld-Verified | 100.0% | estimated ± 1.9 pp, low confidence |
| Vals GPQA Diamond | 93.4% | measured |
| Vals LiveCodeBench | 90.5% | measured |
| Vals MMLU-Pro | 92.4% | measured |
| Vals SWE-bench | 100.0% | estimated ± 4.5 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 85.0% | measured |
| VulcanBench v3 | 87.0% | estimated ± 0.7 pp, low confidence |
| AA AutomationBench | 59.4% | measured |
| GDP.pdf | 26.2% | measured |
| AA ITBench | 49.5% | measured |
| AA Tau3 Banking | 47.2% | measured |
| AA Terminal-Bench 2.1 | 91.4% | measured |
| AA Terminal-Bench 4.0 | 52.0% | measured |
| CursorBench 4.0 | 51.8% | measured |
| CWE-bench v1 | 58.0% | measured |
| DeepSWE | 67.4% | measured |
| HLE w/o tools | 60.9% | measured |
| OSWorld 2.0 | 41.7% | measured |
| PostTrainBench v1.1 | 40.2% | measured |
| ProgramBench | 87.6% | measured |
| SWE Multilingual | 89.1% | measured |
| Terminal-Bench 4.0 | 55.8% | measured |
| Terminal-Bench-Science 0.1 | 52.6% | measured |
| Toolathlon-Verified | 77.8% | measured |
| Vibe Code Bench | 100.0% | estimated ± 10.3 pp, low confidence |
| ExploitGym | 24.0% | estimated ± 5.0 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 86.8% | estimated ± 13.6 pp, low confidence |
| MCP Atlas | 85.3% | estimated ± 2.7 pp, low confidence |
| MMLU-ProX | 90.0% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 98.1% | estimated ± 1.1 pp, low confidence |
| NL2Repo | 60.7% | estimated ± 5.1 pp, low confidence |
| NOVA-63 | 62.8% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 100.0% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 90.9% | estimated ± 7.5 pp, low confidence |
| Terminal-Bench 2.0 | 82.7% | estimated ± 5.9 pp, low confidence |
| Toolathlon | 67.2% | estimated ± 1.7 pp, low confidence |
| HealthBench Hard | 35.0% | estimated ± 7.7 pp, low confidence |
| LiveCodeBench Pro | 97.9% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 76.1% | estimated ± 8.9 pp, low confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 84.6% | estimated ± 3.5 pp, medium confidence |
| ResearchClawBench | 21.5% | estimated ± 2.0 pp, medium confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 73.5% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 89.5% | estimated ± 0.6 pp, medium confidence |
| DRACO | 87.3% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 62.5% | estimated ± 1.6 pp, low confidence |
| HealthBench (raw) | 64.9% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 58.0% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 60.0% | estimated ± 1.3 pp, low confidence |
| HealthBench Professional (raw) | 74.3% | estimated ± 5.0 pp, medium confidence |
| HLE-Verified | 54.6% | estimated ± 0.7 pp, medium confidence |
| LABBench2 | 84.1% | estimated ± 1.3 pp, medium confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| Agents' Last Exam | 50.8% | estimated ± 6.3 pp, medium confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, medium confidence |
| MMLU | 96.6% | estimated ± 1.1 pp, low confidence |