Claude Fable 5.1 released with 'insane' scores on Terminal Bench science

TheZachMueller · x · 2026-09-02

Elie Bakouch retweeted and expressed amazement at Claude Fable 5.1's performance on Terminal Bench science tasks, calling the scores 'totally insane'. The model was just officially introduced as one of the world's most advanced for coding and knowledge work, sparking community discussion about its reasoning capabilities.

Related event: Anthropic Releases Claude Fable 5.1 and Mythos 5.1(56 posts)→

Original post →

More from Models

Models channel →