Long-form writing on LongBench-Write-en [2k, 4k)
78.79Sl ScoreQwen-2.5-14B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen-2.5-14Btuning=LongDPO2025.02 | 78.79 | 89.01 | |
| Qwen-2.5-14Btuning=Base2025.02 | 71.38 | 87.5 | |
| Qwen-2.5-14Btuning=DPO2025.02 | 68.94 | 86.5 | |
| GPT-4o2025.02 | 53 | 92.8 | |
| QWQ2025.02 | 33.13 | 93.75 | |
| Llama3.1-8B-instruct2025.02 | 29.2 | 76.1 | |
| Llama3.1-70B-instruct2025.02 | 14.9 | 84.5 |