ResearchTasksScenario UnderstandingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedScenario Understanding (OOD)GPT-4.1-2025-04-14100Success Rate13Feb 26, 2026Scenario Understanding (ID)TIMEOMNI-190.7Accuracy12Feb 26, 2026