Claude Fable 5 (Low) — benchmark results
Provider: Anthropic. Released 2026-06-09. Access: API.
Unified ELO 2007 ± 34, rank #13 of 1844 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Epoch AI - ECI | 161.53 | ECI Score | 97.3 |
| InferenceBench | 8.74 | Speedup Score | 96.4 |
| ARC-AGI-2 | 76.81 | Accuracy (%) | 90.7 |
| Opus Magnum Bench | 49.28 | Human-normalized score (%) | 85.7 |
| ARC-AGI-1 | 90.5 | Accuracy (%) | 79.7 |
| CursorBench 3.1 | 62.1 | Score (%) | 68.3 |
| Vending-Bench 2 | 5018.52 | Money Balance ($) | 61.5 |
| Epoch AI - Mystery Game Puzzles | 15 | Score | 46.3 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-low · How It Works · Data refreshed daily, snapshot 2026-08-06.