Claude Fable 5 (Max) — benchmark results
Claude Fable 5 evaluated at the max reasoning-effort setting. Provider: Anthropic. Released 2026-06-09. Access: API.
Unified ELO 2173 ± 37, rank #6 of 1776 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CursorBench 3.1 | 70.5 | Score (%) | 100 |
| Epoch AI - Cursorbench | 72.9 | Score | 100 |
| Epoch AI - Scicode | 60.19 | Score | 100 |
| FrontierMath - Tier 4 (v2) | 87.8 | Accuracy (%, 41 private v2 problems) | 100 |
| MathArena - ARXIV April | 70.73 | Accuracy (%) | 100 |
| MathArena Arxiv | 87.5 | Accuracy (%) | 100 |
| MedScribe | 88.52 | Score (self-reported) | 100 |
| Vals Index | 75.14 | Score (self-reported) | 100 |
| Vals Multimodal Index | 74.15 | Score (self-reported) | 100 |
| WeirdML | 91.94 | Average Score | 100 |
| CritPt | 28.6 | Accuracy (self-reported) | 99.2 |
| ZeroBench | 23 | Score (%) | 99.2 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-max · How the rankings work · Data refreshed daily, snapshot 2026-07-22.