Up to four models
Qwen3-235B-A22B-Thinking (Jul 2025) vs GPT-5 nano
On the index (GPT-4 = 100), Qwen3-235B-A22B-Thinking (Jul 2025) scores 138 and GPT-5 nano 125. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
138121–154
WeightsOpen
ReleasedJul 2025
Price in / out$0.45 / $3.5
Context128K
Core tests taken1 of 9
GPT-5 nano
125109–141
WeightsClosed
ReleasedAug 2025
Price in / out$0.050 / $0.40
Context400K
Core tests taken3 of 9
Qwen3-235B-A22B-Thinking (Jul 2025) leads GPT-5 nano by 13 points, ahead on 1 of 1 shared core tests, at 8.8× the price.
Test by testthird-party results
Every result as a table
| Test | Qwen3-235B-A22B-Thinking (Jul 2025) | GPT-5 nano |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 80.0% | 69.4% |
| Fiction.LiveBench | 75.0% | 44.4% |
| SimpleQA Verified | 40.4% | 11.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 86.7% | 81.1% |
| FrontierMath (2025 set) | 8.5% | 8.3% |
| FrontierMath tier 4 (2025 set) | 0.0% | 2.1% |
| Coding | ||
| WeirdML | 41.0% | 38.1% |
| Agents | ||
| DTBench | 80.3% | 62.7% |
| LMCA | 29.3% | 7.9% |
| Mystery game puzzles | 9.0% | 9.0% |
Tests at least two of these models have taken. Bold rows are the core tests.