- Intelligence
- 38.4
- Rank 76 of 744 measured models
- Output speed
- 116 t/s
- Rank 138 of 403 measured models
- Price/1M
- $2.07
- Rank 472 of 659 measured models
- Context window
- 524K
- Rank 338 of 1199 measured models
- Cost per task
- $1.13
- Rank 137 of 193 measured models
Mistral Large 4 Preview scores 38.4 on the Artificial Analysis Intelligence Index, ranking 76th of 744 measured models. The closest models on this index are GPT-5.5 (38.4), Claude Sonnet 5 (38.2), and GPT-6 Luna (38.1). At $2.07 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.5 ($11.25) and Claude Sonnet 5 ($4), more expensive than GPT-6 Luna ($0.20). With an output speed of 116 t/s, it is faster than GPT-5.5 (81.9 t/s) and Claude Sonnet 5 (74.9 t/s), about as fast as GPT-6 Luna (116 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok 4.5 (High)
SpaceXSI · $3 · 58.2 t/s
38.8+0.4$358.2 t/sCompare - GPT-5.5
OpenAI · $11.25 · 81.9 t/s
38.4$11.2581.9 t/sCompare - Claude Sonnet 5
Anthropic · $4 · 74.9 t/s
38.2−0.2$474.9 t/sCompare - GPT-6 Luna
OpenAI · $0.20 · 116 t/s
38.1−0.3$0.20116 t/sCompare
