Claude takes 4 of top 5 spots on AA Intelligence Index, Sonnet 5.5 beats Fable 5.1

xiaosun86 · x · 2026-09-29

An observer notes that 4 of the 5 smartest models on the Artificial Analysis Intelligence Index are now Claude, and Sonnet 5.5 scores higher than Fable 5.1 — speculating that whatever Fable version Anthropic is distilling into Opus and Sonnet is "absurdly" effective.

A replier adds a cynical industry take: consulting businesses like keeping competitors differentiated but within reach, so clients keep paying bench and consulting fees — better to just monetize what works or solve hard problems. Figures are third-party citations; check AA's original release for exact methodology.

Related event: AA Benchmarks: Sonnet 5.5 Nears Opus 5.5 but Sets Output Token Record(12 posts)→

Original post →

More from Models

Models channel →