Up to four models
Claude Sonnet 4 vs Qwen3-30B-A3B-Thinking (Jul 2025)
On the index (GPT-4 = 100), Claude Sonnet 4 scores 133 and Qwen3-30B-A3B-Thinking (Jul 2025) 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
131115–147
WeightsOpen
ReleasedJul 2025
Price in / out–
Context–
Core tests taken1 of 9
Claude Sonnet 4 and Qwen3-30B-A3B-Thinking (Jul 2025) are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Claude Sonnet 4
Qwen3-30B-A3B-Thinking (Jul 2025)
Every result as a table
| Test | Claude Sonnet 4 | Qwen3-30B-A3B-Thinking (Jul 2025) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 79.2% | 70.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 71.1% | 70.3% |
| Agents | ||
| DTBench | 77.1% | 69.3% |
| LMCA | 29.0% | 19.5% |
Task length · METR37 sec
Tests at least two of these models have taken. Bold rows are the core tests.