Z.ai
GLM 5.2
Release date: 6/13/2026
An open-weight bilingual reasoning model tuned for code and long-context analysis.
Pramaana IndexAccuracy: StandardLatency: StrongCost: Leading
- Accuracy / Pramaana Index
- 64.79%± 1.67
- Latency / Pramaana Index
- 348.43s
- Cost / Test / Pramaana Index
- $0.37
- Context window
- 256k
- Max output tokens
- 64k
- Input modality
- Text · Image
Hyperparameter settings
temperature: 0.2
reasoning: extended
fallbacks: disabled
Benchmark performance for GLM 5.2
| Benchmarks | Accuracy | Ranking |
|---|---|---|
| Pramaana Index | 64.79% ± 1.67 | 7 / 35 |
| Pramaana Multimodal Index | 60.71% ± 0.48 | 9 / 24 |
| Legal Research Fidelity | 59.19% ± 0.65 | 7 / 18 |
| Financial Modeling Agent | 57.30% ± 0.82 | 6 / 22 |
| Clinical Documentation Safety | 58.49% ± 0.99 | 8 / 19 |
| MATH-500 | 72.59% ± 1.16 | 10 / 112 |
| GPQA Diamond | 76.60% ± 1.33 | 9 / 121 |
| MMLU-Pro | 74.09% ± 1.50 | 8 / 119 |
| Adaptive Tutoring Dialogue | 60.39% ± 1.67 | 8 / 16 |
| SWE-bench Verified | 56.10% ± 0.48 | 5 / 69 |
| LiveCodeBench | 73.01% ± 0.65 | 6 / 127 |
| Agentic Reliability | 48.91% ± 0.82 | 9 / 12 |
| Strategic Games Arena | 57.00% ± 0.99 | 8 / 20 |
| Benefits Navigator | 60.30% ± 1.16 | 8 / 16 |