ResearchDatasetsCP-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCounter-Perception DiscriminationCP-Bench (dev)94.3F1 Score25Counter-Perception DiscriminationCP-Bench (test)86F1 Score25