Fable 5 excels at postdoc-level math, reversing Anthropic's historical underperformance

davidad · x · 2026-08-22

A user notes that Fable 5 performs exceptionally well on postdoc-level math tasks, placing it in a "completely different league." Historically, Anthropic models have underperformed in higher math compared to OpenAI models, likely due to less math literature in their data mix. Fable 5 is cited as the only exception so far.

Related event: Fable 5 Shows Doctoral-Level Math Prowess, Sparking Opus 5 Comparison(2 posts)→

Original post →

More from Models

Models channel →