Helpfulness Evaluation on Manual Evaluation Set
4.57Average Helpfulness ScoreMSelf-MOA
Evaluation results
| Method | Links | |
|---|---|---|
| MSelf-MOAModel Family=gemma-32026.03 | 4.57 | |
| MSelf-MOAModel Family=llama2026.03 | 4.57 | |
| MSelf-MOAModel Family=gemma-32026.03 | 4.57 | |
| MSelf-MOAModel Family=llama2026.03 | 4.57 | |
| MSelf-MOAModel Family=gemma-22026.03 | 4.53 | |
| MPKU-RLHFModel Family=gemma-22026.03 | 4.53 | |
| MSelf-MOAModel Family=gemma-22026.03 | 4.53 | |
| MPKU-RLHFModel Family=gemma-22026.03 | 4.53 | |
| MbaseModel Family=gemma-32026.03 | 4.47 | |
| MbaseModel Family=llama2026.03 | 4.47 | |
| MbaseModel Family=gemma-32026.03 | 4.47 | |
| MbaseModel Family=llama2026.03 | 4.47 | |
| MSelf-MOAModel Family=qwen2026.03 | 4.43 | |
| MPKU-RLHFModel Family=gemma-32026.03 | 4.43 | |
| MSelf-MOAModel Family=qwen2026.03 | 4.43 | |
| MPKU-RLHFModel Family=gemma-32026.03 | 4.43 | |
| MPKU-RLHFModel Family=qwen2026.03 | 4.4 | |
| MPKU-RLHFModel Family=qwen2026.03 | 4.4 | |
| MbaseModel Family=gemma-22026.03 | 4.37 | |
| MbaseModel Family=gemma-22026.03 | 4.37 | |
| MPKU-RLHFModel Family=llama2026.03 | 4.27 | |
| MPKU-RLHFModel Family=llama2026.03 | 4.27 | |
| MbaseModel Family=qwen2026.03 | 4.13 | |
| MbaseModel Family=qwen2026.03 | 4.13 |