Mistral
Mistral Medium
Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost.
Introducing Mistral 3Model Snapshot
TypeLanguage
ReleaseMay 7, 2025
Context128,000
Tagstool-use, vision
Overall
Rank #452 across 526
9.0
Coding
No rank
n/a
Blended Price
Rank #300 across 357
$4.09/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed66.1 tok/s
First Token0.51s
Max Output64,000
Pricing
Blended$4.09/M
Input$2.75/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 9.0 | #452 |
| MMLU-Pro | reasoning | 49.1% | #296 |
| GPQA | reasoning | 34.9% | #436 |
| Humanity's Last Exam | reasoning | 3.4% | #484 |
| LiveCodeBench |