| Benchmark | GLM-5.2 Full Open Source | GPT-4o mini |
|---|---|---|
| AA Agentic Index | 45.7 | 1 |
| AA Intelligence | 52.6 | 7 |
| ARC-AGI-2 | 22.8 | 0 |
| Artificial Analysis Coding Index | 68.8 | 11.4 |
| gdpval | 50.3 | 0 |
| GPQA Diamond | 91.2 | 42.6 |
| HLE | 54.7 | 4.2 |
| IFBench | 73.3 | 31 |
| scicode | 50.5 | 22.9 |
| simplebench | 58.8 | 10.7 |
| TauBench V3 - Banking | 34.6 | 2.9 |
| Terminal-Bench 2.1 | 82.7 | 5.6 |
| τ³-Bench | 26.8 | 2.9 |
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.