Claude Fable 5 — benchmark results
Anthropic Claude Fable 5, the generally available Claude 5-family frontier model for high-end reasoning, coding, and agentic tasks. Provider: Anthropic. Released 2026-06-09. Access: API.
Unified ELO 2088 ± 25, rank #12 of 1776 rated models, from 160 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Agent Security League - Security Correctness | 29 | Security Correctness (%) | 100 |
| Android Bench | 84.5 | Score (%) | 100 |
| Appwrite Arena (Without Skills) | 97.7 | Overall Score (%) | 100 |
| ArxivMath | 78.6 | Score (self-reported) | 100 |
| Blueprint-Bench 2 | 0.39 | Connectivity Similarity Score | 100 |
| BrowseComp (Fable/Mythos Multi-Agent) | 93.3 | Score (%) | 100 |
| Chatbot Arena (Text) | 1507 | Elo | 100 |
| Chatbot Arena (Vision) | 1318 | Arena Score | 100 |
| ClawArena | 70.05 | Composite Reliability Score | 100 |
| Design Arena (Data Viz) | 1358 | Elo | 100 |
| Design Arena (Game Dev) | 1396 | Elo | 100 |
| Design Arena (SVG) | 1352 | Elo | 100 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.