Up to four models
Qwen3.6-35B-A3B vs Qwen3-235B-A22B-Thinking (Jul 2025)
On the index (GPT-4 = 100), Qwen3.6-35B-A3B scores 139 and Qwen3-235B-A22B-Thinking (Jul 2025) 138. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
139122–155
WeightsOpen
ReleasedApr 2026
Price in / out$0.10 / $0.90
Context262K
Core tests taken2 of 9
138121–154
WeightsOpen
ReleasedJul 2025
Price in / out$0.45 / $3.5
Context128K
Core tests taken1 of 9
Qwen3.6-35B-A3B and Qwen3-235B-A22B-Thinking (Jul 2025) are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 4.0× less.
Test by testthird-party results
Every result as a table
| Test | Qwen3.6-35B-A3B | Qwen3-235B-A22B-Thinking (Jul 2025) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 84.9% | 80.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 86.7% | 86.7% |
| Coding | ||
| WeirdML | 34.5% | 41.0% |
| Agents | ||
| DTBench | 73.9% | 80.3% |
| LMCA | 29.7% | 29.3% |
| Mystery game puzzles | 22.0% | 9.0% |
Tests at least two of these models have taken. Bold rows are the core tests.