ResearchDatasetsFilice et al.FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDownstream RAG UtilityFilice et al. Unseen open-ended56.01BEM18Downstream RAG UtilityFilice et al. Unseen complex57.99BEM18