- Intelligence
- 56.0
- Rank 2 of 744 measured models
- Output speed
- 129 t/s
- Rank 118 of 403 measured models
- Price/1M
- $4
- Rank 532 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $5.46
- Rank 188 of 193 measured models
Claude Sonnet 5.5 (Max, Default Fallback) scores 56.0 on the Artificial Analysis Intelligence Index, ranking 2nd of 744 measured models. The closest models on this index are Claude Opus 5.5 (Default Fallback) (57.6), Muse Wonder Full (Max) (55.8), and Claude Fable 5.1 (Default Fallback) (53.4). At $4 per million tokens (3:1 input/output blended price), it is cheaper than Claude Opus 5.5 (Default Fallback) ($8) and Claude Fable 5.1 (Default Fallback) ($20). With an output speed of 129 t/s, it is faster than Claude Opus 5.5 (Default Fallback) (95.2 t/s) and Claude Fable 5.1 (Default Fallback) (71.1 t/s).
Additional benchmarks6
Design Arena · 3d69.5%
Design Arena · Codecategories60.3%
Design Arena · Dataviz66.3%
Design Arena · Gamedev71.9%
Design Arena · Uicomponent63.7%
Design Arena · Website56.1%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Opus 5.5 (Default Fallback)
Anthropic · $8 · 95.2 t/s
57.6+1.6$895.2 t/sCompare - Muse Wonder Full (Max)
Meta · — · —
55.8−0.2——Compare - Claude Fable 5.1 (Default Fallback)
Anthropic · $20 · 71.1 t/s
53.4−2.6$2071.1 t/sCompare - GPT-6 Astra
OpenAI · $20 · 43.9 t/s
52.7−3.3$2043.9 t/sCompare
