zai-org/glm-4-9b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| GSM8K | math | 84.0 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | | |
| C-Eval | knowledge | 77.1 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | | |
| MMLU | knowledge | 74.7 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | | |
| HumanEval | coding | 70.1 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | | |
| GPQA | reasoning | 34.3 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | | |
| MATH | math | 30.4 | high | | GLM-4-9B | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1** | |
none scraped.