Claude Fable 5.1: benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1808 ± 1, rank #3 of 1392 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchLM | 83 | Overall Score | 100 |
| Blueprint-Bench 2 | 0.42 | Connectivity Similarity Score | 100 |
| Design Arena (Data Viz) | 1371 | Elo | 100 |
| Design Arena (Game Dev) | 1430 | Elo | 100 |
| FrontierSWE V2 | 56.3 | Mean@5 Score (%) | 100 |
| Gert Labs Rankings | 74.45 | GScore (%) | 100 |
| LLM Stats (GDPval-AA) | 1853 | ELO | 100 |
| LLM Stats (OSWorld 2.0) | 77.9 | Score (%) | 100 |
| Mercor APEX | 47.4 | Best Pass@1 (%) | 100 |
| ParseBench | 78.92 | Overall Score | 100 |
| SimpleBench | 86.6 | Score (AVG@5) | 100 |
| Terminal-Bench 4.0 (Claude Code) | 57.9 | Accuracy (%) | 100 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1 · How It Works · Data refreshed daily, snapshot 2026-09-05.