Mistral
Mistral Small 4 (Reasoning) 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 #234 across 526
Rank #177 across 436
Rank #93 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 | 20.8 | #234 |
| Artificial Analysis Coding Index | coding | 24.3 | #177 |
| GPQA | reasoning | 76.9% | #149 |
| Humanity's Last Exam | reasoning | 9.5% | #181 |
| SciCode |
| coding, reasoning |
| 38.0% |
| #151 |
| Output Speed | speed | 167.3 tok/s | #54 |
| Time to First Token | speed | 0.55s | #56 |
| Blended Price | cost | $0.262/M | #93 |
| Input Price | cost | $0.150/M | #89 |
| Output Price | cost | $0.600/M | #105 |
| Value Index | cost, overall | 79.4 | #83 |