ResearchDatasetsRefuteBenchRefuteBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsEmail WritingRefuteBench Email Writing 1.0 (test)98FA7Machine TranslationRefuteBench Machine Translation 1.0 (test)87.6FA7Question AnsweringRefuteBench 1.0 (test)98.5FA7