Up to four models
o1 vs Mistral Large 2 (Nov 2024)
On the index (GPT-4 = 100), o1 scores 136 and Mistral Large 2 (Nov 2024) 110. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
11094–127
WeightsOpen
ReleasedNov 2024
Price in / out–
Context–
Core tests taken1 of 9
o1 leads Mistral Large 2 (Nov 2024) by 25 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
o1
Mistral Large 2 (Nov 2024)
Every result as a table
| Test | o1 | Mistral Large 2 (Nov 2024) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 76.8% | 51.3% |
| Maths | ||
| AIME-style maths (OTIS mock) | 73.3% | 7.8% |
| MATH (level 5) | 94.7% | 50.3% |
| FrontierMath (2025 set) | 9.3% | 0.3% |
| Agents | ||
| DTBench | 74.7% | 60.8% |
Task length · METR31 sec
Tests at least two of these models have taken. Bold rows are the core tests.