Up to four models
GLM-5.3 vs Qwen3.7 Flash
On the index (GPT-4 = 100), GLM-5.3 scores 168 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.
168152–184
WeightsOpen
ReleasedAug 2026
Price in / out$0.070 / $1.4
Context1.05M
Core tests taken5 of 9
138121–155
WeightsClosed
ReleasedJul 2026
Price in / out$0.030 / $0.13
Context1M
Core tests taken2 of 9
GLM-5.3 leads Qwen3.7 Flash by 30 points, ahead on 2 of 2 shared core tests, at 7.3× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.3 | Qwen3.7 Flash |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 90.9% | 82.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 68.8% | 19.3% |
| AIME-style maths (OTIS mock) | 91.1% | 86.7% |
| Agents | ||
| Mystery game puzzles | 33.0% | 15.0% |
Tests at least two of these models have taken. Bold rows are the core tests.