Mistral flagship model with 128K context. Strong instruction following (90/100) and code (88/100). European leader in frontier AI.
Metrics
Provider
Mistral AI
Organization that created the model
Open Source
No
Open source availability
Open Weights
No
Model weights publicly available
Context Window
128,000
Maximum input token capacity
Score Breakdown
code
20%88
Code generation, understanding, and debugging
math
20%85
Mathematical reasoning and problem solving
reasoning
15%86
Multi-step logical reasoning
intelligence
30%87
Overall reasoning and task completion ability
instruction following
90
Compatibility(3)
Sources(2)
Developed by
Mistral AIBenchmark Performance
Compare Models| Dimension | Score |
|---|---|
| Intelligence | 87.0 |
| Reasoning | 86.0 |
| Math | 85.0 |
| Code | 88.0 |
| Instruction Following | 90.0 |
| Overall | 88 |
Loading chart...
Data: Epoch AI (CC-BY 4.0)