ResearchTasksRecall-intensive Question AnsweringFor AI assistantsMarkdownContent indexRecall-intensive Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRecall-intensive tasks (SWDE, SQuAD, TQA, NQ, Drop) truncated to 2K tokens (test)StateX56.1SWDE5Apr 8, 2026
Recall-intensive tasks (SWDE, SQuAD, TQA, NQ, Drop) truncated to 2K tokens (test)StateX56.1SWDE5Apr 8, 2026