ResearchDatasetsReviseQAReviseQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsScientific Paper RevisionReviseQA56.42LC Win Rate (Title)13Scientific Paper RevisionReviseQA Human Evaluation 1.0 (held-out QA benchmark)3.83Judge 1 Score8