LMArena: Claude Fable 5 Score Preview Post-Redeployment

arena · x · 2026-07-03

LMArena collected thousands of votes to compare Claude Fable 5's performance across text, vision, docs, code, and Agent arenas before and after its latest redeployment. Results show largely consistent scores, with Fable 5 maintaining frontier-level performance in text, docs, vision, and frontend code arenas. A roughly 20-point drop in frontend remains within the confidence interval, and the scores continue to stabilize.

Original post →

More from Research

Research channel →