Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Reward Model Evaluation on Alpaca-Eval

72.59LC Win Rate

FiMi-RM

62.29464.96767.6470.313May 19, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
72.5976.39543125
2025.05
71.3875.58512115
2025.05
69.2274.54620144
2025.05
68.2573.84638148
2025.05
66.6867.77534123
2025.05
63.4665.24684168
2025.05
62.9165.77756179
2025.05
62.6965.62712158