ResearchDatasetsGatherFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGoal PredictionGather OOD46.7Classification Accuracy15Goal PredictionGather ID60Classification Accuracy15Image Generation FidelityGather OOD free-response77.16Visual Reward3