MMToM-QA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MMToM-QA
98.5Overall Accuracy
44
MMToM-QA human 1.0 (test)
100Sub-score 1.1
20
MMToM-QA Text-only
1Belief Inference 1.1
17
MMToM-QA Multimodal
95.8Belief Inference 1.1
14
MMToM-QA Video-only
69.1Belief Inference 1.1
13