ToM-BPD
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ToM-BPD (test)
39.78Strategy Accuracy
27
ToM-BPD (test)
54.64Belief Accuracy
27
ToM-BPD (test)
72.82Desire Accuracy
27
ToM-BPD interactive evaluation
55.23Win Rate: Identification
3
Loading the SOTA2 catalog…