ResearchDatasetsFilice et al.Filice et al.FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsDownstream RAG UtilityFilice et al. Unseen open-ended56.01BEM18Downstream RAG UtilityFilice et al. Unseen complex57.99BEM18