Up to four models
GPT-5.5 vs Qwen3.6-35B-A3B
On the index (GPT-4 = 100), GPT-5.5 scores 172 and Qwen3.6-35B-A3B 139. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 of 9
139122–155
WeightsOpen
ReleasedApr 2026
Price in / out$0.10 / $0.90
Context262K
Core tests taken2 of 9
GPT-5.5 leads Qwen3.6-35B-A3B by 33 points, ahead on 2 of 2 shared core tests, at 37× the price.
Test by testthird-party results
GPT-5.5
Qwen3.6-35B-A3B
Every result as a table
| Test | GPT-5.5 | Qwen3.6-35B-A3B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.0% | 84.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 85.3% | 20.3% |
| AIME-style maths (OTIS mock) | 100.0% | 86.7% |
| Surface Evolver Bench | 88.1% | 44.4% |
| Coding | ||
| WeirdML | 84.9% | 34.5% |
| Agents | ||
| DTBench | 96.0% | 73.9% |
| LMCA | 54.3% | 29.7% |
| Mystery game puzzles | 56.0% | 22.0% |
Tests at least two of these models have taken. Bold rows are the core tests.