ResearchTasksComplex Scene ReasoningComplex Scene ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSEEDBenchSceneAlign77.03Accuracy (All)17Feb 26, 2026EMMA miniSceneAlign25.25Score17Feb 26, 2026