ResearchTasksRAG Utility EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSciFactNo Defense85.1Hit Rate7May 4, 2026ArguAnaCleanBase55.6Hit Rate7May 4, 2026FiQANo Defense49.4Hit Rate7May 4, 2026FEVERPromptGuard77Hit Rate6May 4, 2026HotpotQANo Defense81Hit Rate6May 4, 2026NQNo Defense52.2Hit Rate6May 4, 2026