ResearchDatasetsOut-of-Domain (OOD) AggregateFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVisual ReasoningOut-of-Domain (OOD) Aggregate (HalluBench, MathVista, MathVerse, MathVision)0.553OOD Avg Accuracy5
Visual ReasoningOut-of-Domain (OOD) Aggregate (HalluBench, MathVista, MathVerse, MathVision)0.553OOD Avg Accuracy5