Subjective Alignment on AlignBench
6.8Subjective Score (0-10)InternLM2-Chat-20B
Evaluation Results
| Method | Links | |
|---|---|---|
| InternLM2-Chat-20BCategory=~20B Models, Parameter Size=20B, Strategy=RLHF2024.03 | 6.8 | |
| InternLM2-Chat-7BCategory=~7B Models, Parameter Size=7B, Strategy=RLHF2024.03 | 6.1 | |
| GPT-3.5Category=API Models2024.03 | 5.7 | |
| Qwen-14B-ChatCategory=~20B Models, Parameter Size=14B2024.03 | 5.4 | |
| Baichuan2-13B-ChatCategory=~20B Models, Parameter Size=13B2024.03 | 5.3 | |
| InternLM2-Chat-20B-SFTCategory=~20B Models, Parameter Size=20B, Strategy=SFT2024.03 | 5.3 | |
| Baichuan2-7B-ChatCategory=~7B Models, Parameter Size=7B2024.03 | 5.1 | |
| ChatGLM3-6BCategory=~7B Models, Parameter Size=6B2024.03 | 5 | |
| InternLM2-Chat-7B-SFTCategory=~7B Models, Parameter Size=7B, Strategy=SFT2024.03 | 4.9 | |
| Qwen-7B-ChatCategory=~7B Models, Parameter Size=7B2024.03 | 4.7 |