GLM-5.2 High
| Released | 2026-06-13 |
|---|---|
| Price per 1M | $1.20 in · $4.18 out |
| Overall score | 57.0 (early, few results) |
| Context window | 1,000,000 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 57.0 | 3 | |
| Overall: Coding | 56.9 | 3 | |
| Overall: Reasoning | 57.2 | 1 | |
| Overall: Agentic work | 57.0 | 3 | |
| Overall: Frontend | 56.8 | 2 | |
| Coding | 56.8 | 2 | |
| Reasoning | 57.2 | 1 | |
| Value vs price | +4.9 |
Evidence
Coding 56.8 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 36.3% | Epoch AI | 2026-11-11 |
| SWE-rebench | 62.9% | SWE-rebench | 2026-07-01 |
Reasoning 57.2 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 74.3% | Lech Mazur | 2026-11-10 |
Names matched to this model
glm-5-2-high