| Benchmark | Gemini 1.5 Pro | GLM-5.2 Full Open Source |
|---|---|---|
| AA Intelligence | 10 | 52.6 |
| ARC-AGI-2 | 0.8 | 22.8 |
| Artificial Analysis Coding Index | 23.6 | 68.8 |
| GPQA Diamond | 59.1 | 91.2 |
| HLE | 4.9 | 54.7 |
| scicode | 29.5 | 50.5 |
| simplebench | 27.1 | 58.8 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.