ResearchTasksLong-context Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHotpotQA LongBench (test)MemDefrag39String Match3Jul 8, 20262WikiMultihopQA LongBench (test)MemDefrag36String Match3Jul 8, 2026InfiniteBench long-context EN.QACGLS53.9Accuracy3Jul 7, 2026LongBench 1M v2MemReread33.5Easy Difficulty Accuracy3May 12, 2026Page 5 of 5PreviousNext