ResearchTasksLong Video ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLongVideoReason (eval)VideoZoomer80.3Accuracy20May 8, 2026LongVideoBenchGPT-4o66.7Score15Jun 5, 2026WorldSenseFull Tokens52.5Overall Accuracy13May 27, 2026VideoMMMUGPT-4o61.2Overall Score8Feb 26, 2026VideoMMLU (quiz)VideoZoomer67.9Quiz Score7Feb 26, 2026