Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1711 ± 1, rank #83 of 1761 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Humanities & Social Sciences | 60 | Accuracy (%) | 98.8 |
| AA Omniscience - Science, Engineering & Mathematics | 55.2 | Accuracy (%) | 98.2 |
| AA-Omniscience Accuracy | 60.23 | Accuracy (%) | 98.1 |
| AA Omniscience - Business | 50.2 | Accuracy (%) | 97.9 |
| AA Omniscience | 34.13 | Score | 97.7 |
| AA Humanity's Last Exam | 48.89 | Accuracy (%) | 97.3 |
| AA Omniscience - Law | 60.1 | Accuracy (%) | 97.3 |
| AA Omniscience - Health | 51.4 | Accuracy (%) | 96.9 |
| AA Omniscience - Software Engineering (SWE) | 84.5 | Accuracy (%) | 96.7 |
| AA CritPt | 27.71 | Accuracy (%) | 96.6 |
| Artificial Analysis Intelligence Index | 47.78 | Intelligence Index | 96 |
| AA Long Context Reasoning | 82.33 | Accuracy (%) | 95.8 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-adaptive-reasoning-low-effort-default-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.