Up to four models
Qwen3.6-35B-A3B vs Qwen3.7 Flash
On the index (GPT-4 = 100), Qwen3.6-35B-A3B scores 139 and Qwen3.7 Flash 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
138121–155
WeightsClosed
ReleasedJul 2026
Price in / out$0.030 / $0.13
Context1M
Core tests taken2 of 9
Qwen3.6-35B-A3B and Qwen3.7 Flash are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, at 5.5× the price.
Test by testthird-party results
Every result as a table
| Test | Qwen3.6-35B-A3B | Qwen3.7 Flash |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 84.9% | 82.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 20.3% | 19.3% |
| AIME-style maths (OTIS mock) | 86.7% | 86.7% |
| Agents | ||
| Mystery game puzzles | 22.0% | 15.0% |
Tests at least two of these models have taken. Bold rows are the core tests.