Up to four models
Mistral Small 3.2 vs Mistral Small 3.1
On the index (GPT-4 = 100), Mistral Small 3.2 scores 117 and Mistral Small 3.1 108. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
117101–134
WeightsOpen
ReleasedJun 2025
Price in / out$0.075 / $0.20
Context256K
Core tests taken1 of 9
10892–124
WeightsOpen
ReleasedMar 2025
Price in / out$0.35 / $0.56
Context128K
Core tests taken1 of 9
Mistral Small 3.2 leads Mistral Small 3.1 by 9 points, ahead on 1 of 1 shared core tests, and costs 3.8× less.
Test by testthird-party results
Every result as a table
| Test | Mistral Small 3.2 | Mistral Small 3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 49.0% | 47.5% |
| Maths | ||
| AIME-style maths (OTIS mock) | 30.3% | 5.8% |
| Agents | ||
| DTBench | 59.9% | 58.6% |
Tests at least two of these models have taken. Bold rows are the core tests.