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

CharacterBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Role-playingCharacterBench
MC4.525
50
Role-playingCharacterBench latest (full)
Overall Score4.525
47
Role-playingCharacterBench 1.0 (test)
MC4.444
28
Showing 3 of 3 rows