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

BenchmarkScoreMetricPercentile
Agent Security League - Security Correctness29Security Correctness (%)100
Android Bench84.5Score (%)100
Appwrite Arena (Without Skills)97.7Overall Score (%)100
ArxivMath78.6Score (self-reported)100
Blueprint-Bench 20.39Connectivity Similarity Score100
BrowseComp (Fable/Mythos Multi-Agent)93.3Score (%)100
Chatbot Arena (Text)1507Elo100
Chatbot Arena (Vision)1318Arena Score100
ClawArena70.05Composite Reliability Score100
Design Arena (Data Viz)1358Elo100
Design Arena (Game Dev)1396Elo100
Design Arena (SVG)1352Elo100

Interactive version: theaggregate.ai/model?slug=claude-fable-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.