Mistral
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 3Rank #543 across 600
No rank
Rank #271 across 379
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 3.6 | #543 |
| MMLU-Pro | reasoning | 49.1% | #263 |
| GPQA | reasoning | 34.9% | #486 |
| Humanity's Last Exam | reasoning | 3.4% | #535 |
| LiveCodeBench |
| coding |
| 9.9% |
| #315 |
| SciCode | coding, reasoning | 11.8% | #486 |
| MATH-500 | math | 40.5% | #182 |
| AIME | math | 3.7% | #161 |
| Blended Price | cost | $3.00/M | #271 |
| Input Price | cost | $1.50/M | #276 |
| Output Price | cost | $7.50/M | #265 |
| Value Index | cost, overall | 1.2 | #362 |