- Intelligence
- 57.6
- Rank 1 of 744 measured models
- Output speed
- 95.2 t/s
- Rank 177 of 403 measured models
- Price/1M
- $8
- Rank 603 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $5.98
- Rank 191 of 193 measured models
Claude Opus 5.5 (Max, Default Fallback) scores 57.6 on the Artificial Analysis Intelligence Index, ranking 1st of 744 measured models. The closest models on this index are Claude Sonnet 5.5 (Default Fallback) (56.0), Muse Wonder Full (Max) (55.8), and Claude Fable 5.1 (Default Fallback) (53.4). At $8 per million tokens (3:1 input/output blended price), it is cheaper than Claude Fable 5.1 (Default Fallback) ($20), more expensive than Claude Sonnet 5.5 (Default Fallback) ($4). With an output speed of 95.2 t/s, it is faster than Claude Fable 5.1 (Default Fallback) (71.1 t/s), slower than Claude Sonnet 5.5 (Default Fallback) (129 t/s).
Additional benchmarks8
Design Arena · 3d72.1%
Design Arena · Codecategories63.8%
Design Arena · Dataviz64.8%
Design Arena · Gamedev71.7%
Design Arena · Mobileapps64.2%
Design Arena · Svg51.8%
Design Arena · Uicomponent63.3%
Design Arena · Website57.5%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Sonnet 5.5 (Default Fallback)
Anthropic · $4 · 129 t/s
56.0−1.6$4129 t/sCompare - Muse Wonder Full (Max)
Meta · — · —
55.8−1.8——Compare - Claude Fable 5.1 (Default Fallback)
Anthropic · $20 · 71.1 t/s
53.4−4.2$2071.1 t/sCompare - GPT-6 Astra
OpenAI · $20 · 43.9 t/s
52.7−4.9$2043.9 t/sCompare
