Anthropic launches Claude Sonnet 5.5: 56 on AA Index, just 2 points behind Opus 5.5

jarrodwatts · x · 2026-09-29

Per Artificial Analysis, Anthropic has launched Claude Sonnet 5.5, scoring 56 on its Intelligence Index — just 2 points behind Opus 5.5 (max) and #2 overall. With max effort it gains 18 points over Sonnet 5, while posting the highest Output Tokens per Task seen yet. Pricing is unchanged from Sonnet 5 at $0.2/$2/$10 per 1M cache input/input/output tokens. Takeaway: flagship-level ability at the same price, but with heavier per-task output token spend.

Related event: Sonnet 5.5 nearly matches Opus 5.5 in benchmarks but burns tokens at record levels(7 posts)→

Original post →

More from Models

Models channel →