ResearchTasksProcedural Temporal UnderstandingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTPRU (test)TPRU-7B75.7Accuracy7Feb 26, 2026LEGO-Puzzles (test)TPRU-7B42.82Overall Accuracy7Feb 26, 2026MuirBench (test)TPRU-7B65.04Overall Score7Feb 26, 2026