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

PersonaGym

Benchmarks

Task NameDataset NameSOTA ResultTrend
Role-playingPersonaGym
Engagement (EA)4.98
7
Role-playing Agent EvaluationPersonaGym
Action Justification4.13
4
Showing 2 of 2 rows