Up to four models
Qwen 3.5 Flash (hosted 35B-A3B) vs Qwen 3.6 Flash
On the index (GPT-4 = 100), Qwen 3.5 Flash (hosted 35B-A3B) scores 138 and Qwen 3.6 Flash 136. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
138121–155
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken2 of 9
Qwen 3.5 Flash (hosted 35B-A3B) and Qwen 3.6 Flash are too close to call (3 points apart, within the uncertainty), ahead on 0 of 2 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Qwen 3.5 Flash (hosted 35B-A3B) | Qwen 3.6 Flash |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 82.3% | 83.3% |
| SimpleQA Verified | 20.3% | 15.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 18.3% | 22.5% |
| AIME-style maths (OTIS mock) | 84.4% | 84.4% |
| Chess puzzles | 14.0% | 12.0% |
| FrontierMath (2025 set) | 6.2% | 10.3% |
| FrontierMath tier 4 (2025 set) | 0.0% | 0.0% |
| Agents | ||
| DTBench | 82.9% | 77.1% |
| LMCA | 29.1% | 31.0% |
| Mystery game puzzles | 20.0% | 18.0% |
Tests at least two of these models have taken. Bold rows are the core tests.