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

RPR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reward ModelingRPR n=5 (test)
User Friendliness81.2
10
Personalized Preference ModelingRPR (test)
Linguistic Creativity74.04
5
Showing 2 of 2 rows