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

Minimax Role-Play Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Role-PlayMinimax Role-Play Bench Full 17-Model Leaderboard 1.0
Overall Score84.65
17
Role-Play EvaluationMinimax Role-Play Bench
Average Score84.65
17
Showing 2 of 2 rows