Up to four models
o1-mini vs Qwen2.5
On the index (GPT-4 = 100), o1-mini scores 123 and Qwen2.5 112. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
o1-mini leads Qwen2.5 by 11 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
o1-mini
Qwen2.5
Every result as a table
| Test | o1-mini | Qwen2.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 62.4% | 49.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 46.9% | 8.1% |
| MATH (level 5) | 89.2% | 63.2% |
| Coding | ||
| WeirdML | 36.3% | 16.0% |
Task length · METR
21 sec
Tests at least two of these models have taken. Bold rows are the core tests.