ResearchTasksGeneral-purpose RAG evaluationGeneral-purpose RAG evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedKILT, SuperGLUE, AISARES (answer relevance)0.132Kendall's Tau2Jun 30, 2026