Anthropic · model
Claude Fable 5.1 (max with fallback) benchmark scores
As of 2026-10-07, Claude Fable 5.1 (max with fallback) (Anthropic) has measured scores on 13 benchmarks and estimated scores on 2 more.
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Bench 2.1 | 91.4% | measured |
| Terminal-Bench 4.0 | 52.0% | measured |
| Terminal-Bench Science 0.1 | 43.3% | measured |
| GPQA Diamond | 93.7% | measured |
| SciCode | 63.1% | measured |
| CritPt | 29.7% | measured |
| GDP.pdf | 26.2% | measured |
| τ³-Bench Banking | 47.2% | measured |
| MMMU-Pro | 84.8% | estimated ± 2.6 pp, high confidence |
| AA-AnalystAgent | 57.5% | measured |
| Harvey LAB | 93.0% | measured |
| Humanity's Last Exam | 59.1% | measured |
| AutomationBench | 59.4% | measured |
| EnterpriseOps-Gym | 55.4% | estimated ± 1.8 pp, low confidence |
| ITBench SRE | 49.5% | measured |