Up to four models
o1-mini vs Qwen2.5-32B
On the index (GPT-4 = 100), o1-mini scores 123 and Qwen2.5-32B 111. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
o1-mini leads Qwen2.5-32B by 12 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
o1-mini
Qwen2.5-32B
Every result as a table
| Test | o1-mini | Qwen2.5-32B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 62.4% | 46.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 46.9% | 7.4% |
| MATH (level 5) | 89.2% | 56.1% |
Tests at least two of these models have taken. Bold rows are the core tests.