ResearchTasksLong-context retrievalFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRULER niah_multikey_1 zeroshot (test)PhiMoE (FP16 baseline)96Accuracy2Apr 23, 2026RULER niah_single_2 zeroshot (test)PhiMoE (FP16 baseline)95.5Accuracy2Apr 23, 2026RULER 1MNemotron-3-Ultra 550B-A55B-Base76.83Score1Jun 16, 2026RULER 512KNemotron-3-Ultra 550B-A55B-Base84.54RULER 512K Score1Jun 16, 2026Page 4 of 4PreviousNext