ResearchTasksLong-context language evaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLongBench v1 (test)LOOKAHEADKV19.6NrtQA Score31Mar 12, 2026LongBenchBaseline48.43SQA19May 25, 2026