Up to four models
DeepSeek-R1-0528 vs Mistral Medium 3
On the index (GPT-4 = 100), DeepSeek-R1-0528 scores 135 and Mistral Medium 3 120. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
120104–136
WeightsClosed
ReleasedMay 2025
Price in / out$0.44 / $2.2
Context131K
Core tests taken2 of 9
DeepSeek-R1-0528 leads Mistral Medium 3 by 15 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | DeepSeek-R1-0528 | Mistral Medium 3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 76.3% | 59.5% |
| Maths | ||
| AIME-style maths (OTIS mock) | 66.4% | 32.2% |
| MATH (level 5) | 96.6% | 81.6% |
Task length · METR
32 sec
Tests at least two of these models have taken. Bold rows are the core tests.