Opus 5.5 called Anthropic's best vision model yet, 60% cheaper with big benchmark gains

scaling01 · x · 2026-09-25

skalskip92 shares preliminary benchmarks calling Opus 5.5 by far the best vision model Anthropic has made — better than Fable 5 and GPT-6 Sol, though behind GPT-6 Astra.

Key numbers:

The author notes every lab is now working on vision, with 16 more examples to come.

Original post →

More from Models

Models channel →