Up to four models
GPT-5.4 vs Qwen3.5
On the index (GPT-4 = 100), GPT-5.4 scores 166 and Qwen3.5 144. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9
144127–161
WeightsOpen
ReleasedFeb 2026
Price in / out$0.45 / $3.0
Context262K
Core tests taken3 of 9
GPT-5.4 leads Qwen3.5 by 22 points, ahead on 3 of 3 shared core tests, at 5.2× the price.
Test by testthird-party results
GPT-5.4
Qwen3.5
Every result as a table
| Test | GPT-5.4 | Qwen3.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 93.3% | 86.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 78.6% | 31.2% |
| AIME-style maths (OTIS mock) | 97.8% | 88.9% |
| Agents | ||
| APEX-Agents | 52.4% | 24.9% |
| DTBench | 94.4% | 87.5% |
| LMCA | 52.0% | 37.9% |
| Mystery game puzzles | 37.0% | 18.0% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.