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

ToMI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Theory of MindToMi
Accuracy100
55
Theory of Mind reasoningToMI False Belief
Accuracy98.2
18
Theory of Mind reasoningToMI (All)
Accuracy87.8
12
Showing 3 of 3 rows