Up to four models
o4-mini vs Qwen3
On the index (GPT-4 = 100), o4-mini scores 141 and Qwen3 133. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
133110–156
WeightsOpen
ReleasedApr 2025
Price in / out$0.12 / $0.50
Context41K
Core tests taken0 of 9
o4-mini and Qwen3 are too close to call (9 points apart, within the uncertainty).
Test by testthird-party results
o4-mini
Qwen3
Every result as a table
| Test | o4-mini | Qwen3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 74.5% | 70.2% |
| MMLU Pro | 80.6% | 81.3% |
| Maths | ||
| MATH 500 | 94.2% | 94.6% |
| MGSM | 93.4% | 92.5% |
| Coding | ||
| LiveCodeBench | 82.2% | 70.6% |
| Professional work | ||
| LegalBench | 79.2% | 80.2% |
| TaxEval v2 | 74.8% | 70.7% |
Task length · METR38 sec
Tests at least two of these models have taken. Bold rows are the core tests.