Mistral
Mistral Medium 3.1 is a Mistral AI model profile from a lineup that spans compact Ministral models, specialist coding models, reasoning-oriented Magistral releases, and larger frontier open models. The local data makes its multilingual, coding, cost, and latency tradeoffs easier to compare against other providers.
Introducing Mistral 3Rank #231 across 526
Rank #228 across 436
Rank #179 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 21.3 | #231 |
| Artificial Analysis Coding Index | coding | 18.3 | #228 |
| Artificial Analysis Math Index | math | 38.3 | #163 |
| MMLU-Pro | reasoning | 68.3% | #235 |
| reasoning |
| 58.8% |
| #306 |
| Humanity's Last Exam | reasoning | 4.4% | #388 |
| LiveCodeBench | coding | 40.6% | #176 |
| SciCode | coding, reasoning | 33.8% | #224 |
| Output Speed | speed | 70 tok/s | #182 |
| Time to First Token | speed | 0.51s | #37 |
| Blended Price | cost | $0.800/M | #179 |
| Input Price | cost | $0.400/M | #177 |
| Output Price | cost | $2.00/M | #184 |
| Value Index | cost, overall | 26.6 | #188 |