Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback): benchmark results
Provider: Anthropic. Released 2026-06-09. Access: API.
Unified ELO 1751 ± 1, rank #27 of 1761 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Business | 57.4 | Accuracy (%) | 100 |
| AA Omniscience - Humanities & Social Sciences | 64.3 | Accuracy (%) | 99.8 |
| AA Omniscience - Software Engineering (SWE) | 91.1 | Accuracy (%) | 99.8 |
| AA Omniscience - Law | 66.2 | Accuracy (%) | 99.6 |
| AA Omniscience - Science, Engineering & Mathematics | 61.28 | Accuracy (%) | 99.6 |
| AA-Omniscience Accuracy | 65.35 | Accuracy (%) | 99.6 |
| AA Humanity's Last Exam | 55.47 | Accuracy (%) | 99.5 |
| AA Terminal-Bench Hard | 62.88 | Accuracy (%) | 99.5 |
| Epoch AI - Scicode | 60.19 | Score | 99.4 |
| AA Omniscience | 43.3 | Score | 99.2 |
| AA Omniscience - Health | 53.72 | Accuracy (%) | 99.2 |
| AA TAU-2 Bench | 98.54 | Accuracy (%) | 99 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-adaptive-reasoning-max-effort-opus-4-8-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.