Up to four models
GLM-5.2 vs Qwen3.7-Plus
On the index (GPT-4 = 100), GLM-5.2 scores 154 and Qwen3.7-Plus 148. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9
148131–165
WeightsClosed
ReleasedJun 2026
Price in / out$0.32 / $1.28
Context1M
Core tests taken3 of 9
GLM-5.2 and Qwen3.7-Plus are too close to call (6 points apart, within the uncertainty), ahead on 3 of 3 shared core tests, at 3.0× the price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.2 | Qwen3.7-Plus |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 91.9% | 87.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 59.2% | 34.4% |
| AIME-style maths (OTIS mock) | 86.4% | 93.3% |
| Coding | ||
| Code Migration | 37.9% | 12.9% |
| Vibe Code Bench v1.1 | 64.0% | 46.4% |
| Agents | ||
| SkillsBench | 45.1% | 54.3% |
| DTBench | 93.6% | 84.0% |
| LMCA | 45.8% | 37.6% |
| Mystery game puzzles | 19.0% | 17.0% |
| Professional work | ||
| Finance Agent (v2) | 49.7% | 38.2% |
| EMB | 61.5% | 49.3% |
| Legal Research Bench | 31.3% | 16.4% |
Tests at least two of these models have taken. Bold rows are the core tests.