Up to four models
Mistral Large 4 vs o3
On the index (GPT-4 = 100), Mistral Large 4 scores 148 and o3 147. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
148132–165
WeightsOpen
ReleasedOct 2026
Price in / out$0.70 / $2.1
Context1.05M
Core tests taken3 of 9
Mistral Large 4 and o3 are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, and costs 3.3× less.
Test by testthird-party results
Every result as a table
| Test | Mistral Large 4 | o3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 88.1% | 81.8% |
| SimpleQA Verified | 20.0% | 49.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 58.6% | 33.3% |
| AIME-style maths (OTIS mock) | 98.3% | 84.4% |
| Chess puzzles | 33.0% | 37.0% |
| Agents | ||
| DTBench | 88.2% | 84.8% |
| LMCA | 35.8% | 39.7% |
| Mystery game puzzles | 17.0% | 29.0% |
Task length · METR39 sec
Tests at least two of these models have taken. Bold rows are the core tests.