Code Interpreter Evaluation on CIBench
57.9English ScoreQwen1.5-14B-Chat
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Qwen1.5-14B-Chatparameter size group=13 ~ 20B Models2024.03 | 57.9 | 49.7 | 53.8 | |
| InternLM2-Chat-7Bparameter size group=< 7B Models2024.03 | 57.1 | 40.7 | 48.9 | |
| InternLM2-Chat-20Bparameter size group=13 ~ 20B Models2024.03 | 56 | 54.7 | 55.4 | |
| Qwen-14B-Chatparameter size group=13 ~ 20B Models2024.03 | 54.8 | 40.8 | 47.8 | |
| InternLM2-Chat-7B-SFTparameter size group=< 7B Models2024.03 | 52.1 | 27.8 | 39.9 | |
| InternLM2-Chat-20B-SFTparameter size group=13 ~ 20B Models2024.03 | 49 | 43.7 | 46.4 | |
| Qwen-7B-Chatparameter size group=< 7B Models2024.03 | 47.8 | 29.2 | 38.5 | |
| Mistral-7B-Instruct-v0.2parameter size group=< 7B Models2024.03 | 47.6 | 38 | 42.8 | |
| Qwen1.5-7B-Chatparameter size group=< 7B Models2024.03 | 44.7 | 26.9 | 35.8 | |
| Mistral-8x7B-Instruct-v0.1parameter size group=13 ~ 20B Models2024.03 | 42.6 | 40.3 | 41.5 | |
| ChatGLM3-6Bparameter size group=< 7B Models2024.03 | 29.4 | 17.1 | 23.2 | |
| Llama2-13B-Chatparameter size group=13 ~ 20B Models2024.03 | 20 | 12.3 | 16.1 | |
| Llama2-7B-Chatparameter size group=< 7B Models2024.03 | 12.2 | 10.6 | 11.4 |