AAII ranking: Opus 5.5 tops overall intelligence, beats Fable 5.1 Max with fewer tokens at xhigh

Angaisb_ · x · 2026-09-23

Per an AAII summary, Claude Opus 5.5 posts the highest overall intelligence score. It uses more output tokens per task than any other model at max reasoning effort, yet at xhigh it scores above Fable 5.1 Max while using fewer tokens.

Related event: Claude Opus 5.5 Launches to Top Rankings with Lower Price and Faster Speed(28 posts)→

Original post →

More from Models

Models channel →