ResearchTasksIn-context recallFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRecall-intensive tasks suiteXfmr++62.3FDA Recall Score12Feb 27, 2026JRT-style cloze (FDA and SWDE datasets) 1.3B / 100B checkpointsOSDN-APF24.1FDA Accuracy2May 14, 2026Recall-intensive tasks suite (test)——FDA0Feb 26, 2026