ResearchDatasetsREPRODUCEBENCHREPRODUCEBENCHFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsExperimental reproductionREPRODUCEBENCH91.57Align-Score (Paper-Level)7Automatic experiment reproductionREPRODUCEBENCH7.36Method Component Score4