Back to models
Intelligence Index
Reasoning setting
38.4#25 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.34 in / ≈ $1.05 out / 1M tokOpenRouter · Mistral · promotional
- Context window
- 1M tok
Performance profile
CodingRank #21 of 94
54.2%
SciCodeCost efficiencyRank #48 of 67
33.8pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Mistral Large 4
Cost per task (USD)
Mistral Large 4Reasoning
- Intelligence Index
- 38.4
- Cost / task
- $1.13
- Evaluation time
- 12.2m
Pricing & access
USD per 1M tokens
- Input
- $0.34
- Output
- $1.045
- Cached input
- $0.035
Benchmarks
Full leaderboardSource (opens in a new tab)35.0%, rank 36 of 12654.2%, rank 21 of 9426.8%, rank 18 of 8781.3%, rank 23 of 1251,422 Elo, rank 29 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 33Motif 3Reasoning37.0%
- 34Qwen3.7 PlusReasoning35.6%
- 35MiMo-V2.6-FlashReasoning35.1%
- 36Mistral Large 4Reasoning35.0%
- 36Kimi K2.7 CodeReasoning35.0%
- 38Beam 1.0Reasoning34.7%
- 39DeepSeek V4 Flash VisionMax34.5%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherMuse Spark OpenExtra high
- Intelligence Index
- 38.9+0.5
- Cost / task
- $0.844−26%
- Higher score, lower costMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+7.9
- Cost / task
- $0.133−88%
- More from Mistral
- Intelligence Index
- 14.2−24.2
- Cost / task
- $0.502−56%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.