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

MuMa-ToM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Theory-of-Mind reasoningMuMA-ToM
Accuracy95.89
40
Social interaction reasoningMuMA-ToM
Belief Score98.9
11
Theory of Mind Question AnsweringMuMa-ToM
Accuracy93.5
5
Showing 3 of 3 rows