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

Human Preference Evaluation on MHP Overall (test)

74.2Preference Accuracy

MPS

62.44865.49968.5571.601May 23, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.05
74.2
2024.05
69.5
2024.05
67.5
2024.05
65.5
2024.05
65.5
2024.05
63.7
2024.05
62.9