ResearchTasksComprehensive long-context evaluationComprehensive long-context evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRULER and LongBench V2Qwen2.5-14B-Instruct-1M65.29Total Average Score12Apr 21, 2026