ResearchDatasetsAverage of 11 datasetsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVision-Language PromptingAverage of 11 datasets80.48HM Score9Base-to-new GeneralizationAverage of 11 datasets (New split)62.51Acc5Base-to-new GeneralizationAverage of 11 datasets (Base)78.77Accuracy5