Fable 5.1 beats Fable 5, matches Opus 5 on ML bench as refusals drop to 0/12

xeophon · x · 2026-09-02

User wassname ran their own wassname-ml-bench to test whether Fable 5.1 was nerfed for ML: it outperforms Fable 5 and is on par with Opus 5 at machine learning. Anthropic also improved refusal classifiers — Fable 5 went from 2/12 to 0/12 refusals, Fable 5.1 sits at 1/12. The test responds to a question citing Anthropic's note on improved cyber/bio classifiers for Fable 5.1, and whether AI-research classifiers still throttle capability.

Original post →

More from Models

Models channel →