Up to four models
Qwen3 vs GPT-4.1 mini
On the index (GPT-4 = 100), Qwen3 scores 133 and GPT-4.1 mini 120. 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
GPT-4.1 mini
120104–136
WeightsClosed
ReleasedApr 2025
Price in / out$0.40 / $1.6
Context1.05M
Core tests taken3 of 9
Qwen3 and GPT-4.1 mini are too close to call (13 points apart, within the uncertainty), and costs 3.3× less.
Test by testthird-party results
Every result as a table
| Test | Qwen3 | GPT-4.1 mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 70.2% | 67.9% |
| MMLU Pro | 81.3% | 77.2% |
| Maths | ||
| MATH 500 | 94.6% | 88.0% |
| MGSM | 92.5% | 87.8% |
| Coding | ||
| LiveCodeBench | 70.6% | 58.2% |
| Professional work | ||
| LegalBench | 80.2% | 78.0% |
| TaxEval v2 | 70.7% | 71.9% |
Tests at least two of these models have taken. Bold rows are the core tests.