ResearchTasksMulti-hop ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMuSiQue (test)ETGPO77.3Mean Accuracy4Feb 26, 2026Musique, HotpotQA, 2Wiki, and Bamboogle 3-hop and aboveSIGHT31.98EM3Feb 26, 2026MuSiQue (val test)ETGPO2,849Token Usage (Optimization Phase)3Feb 26, 2026Multi-hop 2-hop N=500KO79Accuracy2Mar 19, 2026Page 3 of 3PreviousNext