ResearchTasksMental State InferenceFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMToM-QA human 1.0 (test)GPT-4100Sub-score 1.120Feb 26, 2026Augmented CaSiNoNegotiationToM40Accuracy1May 29, 2026