Up to four models
o3 vs Mistral Small 3.1
On the index (GPT-4 = 100), o3 scores 147 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.
10892–124
WeightsOpen
ReleasedMar 2025
Price in / out$0.35 / $0.56
Context128K
Core tests taken1 of 9
o3 leads Mistral Small 3.1 by 39 points, ahead on 1 of 1 shared core tests, at 8.7× the price.
Test by testthird-party results
o3
Mistral Small 3.1
Every result as a table
| Test | o3 | Mistral Small 3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 81.8% | 47.5% |
| GPQA Diamond (Vals AI) | 84.1% | 44.2% |
| MMLU Pro | 85.6% | 66.0% |
| MMMU Pro | 80.4% | 60.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 84.4% | 5.8% |
| MATH (level 5) | 97.8% | 46.8% |
| MATH 500 | 94.6% | 68.4% |
| MGSM | 91.8% | 84.2% |
| Coding | ||
| LiveCodeBench | 83.9% | 31.8% |
| Agents | ||
| DTBench | 84.8% | 58.6% |
| Professional work | ||
| CorpFin v2 | 59.7% | 44.2% |
| LegalBench | 83.8% | 69.2% |
| MortgageTax | 65.7% | 61.2% |
| TaxEval v2 | 74.6% | 58.3% |
Task length · METR39 sec
Tests at least two of these models have taken. Bold rows are the core tests.