Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

PersonalRewardBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Personalized LLM Alignment EvaluationPersonalRewardBench (test)
Mean Score3.354
6
Reward ModelingPersonalRewardBench (test)
Macro Accuracy65.21
6
Showing 2 of 2 rows