Up to four models
Mistral Medium 3.5 vs o3-mini
On the index (GPT-4 = 100), Mistral Medium 3.5 scores 131 and o3-mini 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
131114–148
WeightsOpen
ReleasedApr 2026
Price in / out$1.5 / $7.5
Context262K
Core tests taken1 of 9
Mistral Medium 3.5 and o3-mini are too close to call (0 points apart, within the uncertainty).
Test by testthird-party results
Every result as a table
| Test | Mistral Medium 3.5 | o3-mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 34.8% | 75.5% |
| MMLU Pro | 75.3% | 78.7% |
| Coding | ||
| WeirdML | 43.7% | 43.8% |
| Agents | ||
| DTBench | 75.5% | 68.8% |
| LMCA | 26.1% | 19.0% |
| Professional work | ||
| CorpFin v2 | 58.8% | 45.3% |
| TaxEval v2 | 68.0% | 69.4% |
Tests at least two of these models have taken. Bold rows are the core tests.