Anthropic's Fable 5.1 tops coding benchmark, reaching Pareto frontier

PawelHuryn · x · 2026-09-02

Anthropic's Fable 5.1 achieved top results on the Bug Hunt Bench, marking the first Anthropic model at the Pareto frontier.

Results:

Performance:

Comments noted that while Fable 5 felt good to use, it wasn't previously the best coder, making this result unexpected.

Related event: Anthropic's Fable 5.1 Tops Bug Hunt Bench, Beating GPT-5.6(4 posts)→

Original post →

More from coding & agent

coding & agent channel →