List your company

Long-form writing on LongBench-Write-en [2k, 4k)

78.79Sl ScoreQwen-2.5-14B
12.344429.594746.84564.0953Feb 4, 2025

Evaluation results

MethodLinks
Qwen-2.5-14Btuning=LongDPO2025.0278.7989.01
Qwen-2.5-14Btuning=Base2025.0271.3887.5
Qwen-2.5-14Btuning=DPO2025.0268.9486.5
GPT-4o2025.025392.8
QWQ2025.0233.1393.75
Llama3.1-8B-instruct2025.0229.276.1
Llama3.1-70B-instruct2025.0214.984.5