- Intelligence
- 38.2
- Rank 78 of 744 measured models
- Coding
- 71.5
- Rank 46 of 298 measured models
- Output speed
- 74.9 t/s
- Rank 239 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
- $5.09
- Rank 186 of 193 measured models
Claude Sonnet 5 (Max) scores 38.2 on the Artificial Analysis Intelligence Index, ranking 78th of 744 measured models. The closest models on this index are GPT-5.5 (38.4), Mistral Large 4 Preview (38.4), and GPT-6 Luna (38.1). At $4 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.5 ($11.25), more expensive than Mistral Large 4 Preview ($2.07) and GPT-6 Luna ($0.20). With an output speed of 74.9 t/s, it is slower than GPT-5.5 (81.9 t/s), Mistral Large 4 Preview (116 t/s), and GPT-6 Luna (116 t/s).
Additional benchmarks16
Design Arena · 3d54.1%
Design Arena · Agenticgamedev52.3%
Design Arena · Androidnative54.3%
Design Arena · Asciiart51.4%
Design Arena · Codecategories52.7%
Design Arena · Dataviz52.9%
Design Arena · Fullstack53.7%
Design Arena · Gamedev52.0%
Design Arena · Godotgamedev54.4%
Design Arena · Htmlslides53.7%
Design Arena · Mobileapps50.9%
Design Arena · Python Pptxslides50.1%
Design Arena · Svg49.8%
Design Arena · Uicomponent54.0%
Design Arena · Webapps53.3%
Design Arena · Website52.4%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.5
OpenAI · $11.25 · 81.9 t/s
38.4+0.2$11.2581.9 t/sCompare - Mistral Large 4 Preview
Mistral · $2.07 · 116 t/s
38.4+0.2$2.07116 t/sCompare - GPT-6 Luna
OpenAI · $0.20 · 116 t/s
38.1−0.1$0.20116 t/sCompare - MiMo-V2.6-Flash
Xiaomi · $0.175 · 53.8 t/s
37.9−0.3$0.17553.8 t/sCompare
