| Benchmark | Model | Rank | Results |
|---|---|---|---|
| instruction-following-on-alignbench | GLM-4 (0520) | #4 | Score (0-10): 8.00 |
| instruction-following-on-mtbench | GLM-4-9B-Chat | #9 | Score (1-10): 8.35 |
| multi-task-language-understanding-on-mmmlu | GLM-4-9B-Chat | #13 | Accuracy: 56.6 |
| multi-task-language-understanding-on-c-eval | GLM-4-9B-Chat | #21 | Accuracy: 75.6 |
| arithmetic-reasoning-on-gsm8k | GLM-4 (0520) | #40 | Accuracy: 93.3 |
| math-word-problem-solving-on-math | GLM-4 (0520) | #47 | Accuracy: 61.3 |
| code-generation-on-humaneval | GLM-4 (0520) | #68 | Pass@1: 78.5 |