Leaked benchmarks claim Claude Sonnet 5.5 hits 56 on AA index, beating Opus 5.5

airesearch12 · x · 2026-09-29

LuminaBench claims Claude Sonnet 5.5 scored 56 on the AA intelligence index (vs 48 for "Sol"), and that it somehow beats Opus 5.5 on Terminal-Bench. The tone is meme-heavy and no official source is cited — unverified until Anthropic confirms.

Related event: Rumor: Claude Sonnet 5.5 Scores 56 on Intelligence Index, Nearing Opus 5.5(3 posts)→

Original post →

More from Models

Models channel →