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:
- vs Fable 5.1 (high): estimated cost down 60%, detection up 11.84 pp, reasoning up 12.80 pp
- vs GPT-6 Sol (high): extraction up 11.00 pp, reasoning up 7.95 pp
The author notes every lab is now working on vision, with 16 more examples to come.
More from Models
- NaceAI launches Drex, a sub-6B decision model that tops the public Decision Index at 51.73 — ordax · 2026-09-25
- Model audit showdown: Astra dominates, Opus and Fable close, Grok 4.7 and GPT-6 Sol lag far behind — ivan_bezdomny · 2026-09-25
- Uncensored local model Bonzai 2 27B tops benchmarks, runs on 12GB VRAM — alexcovo_eth · 2026-09-25
- Same prompt, Opus 5.5 one-shot video generation put to a public retest with different tools — drrickio · 2026-09-25
- Users blast GPT-5.2 for rampant false crisis flags and needless helpline redirects — ryunuck · 2026-09-25
- Agent Arena Ranks 43 Models on 2M+ Real-World Agentic Tasks; Claude Fable 5.1 Tops Board — arena · 2026-09-25