GLM-Z1-9B-0414: benchmark results
Provider: Zhipu. Released 2025-04-14. Access: Open.
Aggregate Rating 1535 ± 47, rank #655 of 1635 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - BLUEX | 70.38 | Accuracy (%) | 92 |
| Open Portuguese LLM - FaQuAD NLI | 79.95 | Macro F1 (%) | 88.9 |
| Open Portuguese LLM - ENEM | 74.11 | Accuracy (%) | 86.2 |
| Open Portuguese LLM - ASSIN2 RTE | 90.36 | Macro F1 (%) | 56.7 |
| SuperCLUE General (July 2025) - Math Reasoning | 54.2 | Score | 50 |
| SuiChat-CN - Without Keywords | 65.5 | Macro F1 (%) of suicide-risk level classification of Chinese | 48.8 |
| Open Portuguese LLM - OAB Exams | 39.86 | Accuracy (%) | 42.5 |
| SuiChat-CN - Few-Shot | 65.8 | Macro F1 (%) of suicide-risk level classification of Chinese | 41.9 |
| SuiChat-CN - Without Context | 63.2 | Macro F1 (%) of suicide-risk level classification of Chinese | 41.9 |
| SuperCLUE General (July 2025) - Science Reasoning | 20 | Score | 40.2 |
| SuperCLUE General (July 2025) - Agent | 46.64 | Score | 31.5 |
| SuperCLUE General (July 2025) - Overall | 32.93 | Score | 23.9 |
Interactive version: theaggregate.ai/model?slug=glm-z1-9b-0414 · How It Works · Data refreshed daily, snapshot 2026-11-05.