Up to four models
Grok-3 mini vs Qwen3-235B-A22B
On the index (GPT-4 = 100), Grok-3 mini scores 131 and Qwen3-235B-A22B 130. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Grok-3 mini and Qwen3-235B-A22B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Grok-3 mini
Qwen3-235B-A22B
Every result as a table
| Test | Grok-3 mini | Qwen3-235B-A22B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 76.3% | 70.7% |
| Fiction.LiveBench | 66.7% | 67.7% |
| Maths | ||
| MATH (level 5) | 90.9% | 68.9% |
| Coding | ||
| Aider Polyglot | 49.3% | 59.6% |
| WeirdML | 42.6% | 37.3% |
Tests at least two of these models have taken. Bold rows are the core tests.