ResearchTasksMulti-Doc QAFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLongBench v2 (test)Base86.7Finance Accuracy16Jun 11, 2026HotpotQADense45Accuracy15May 15, 2026LongBenchGPT-3.5-Turbo-16k51.6HotpotQA12Feb 26, 2026LongBench MuSiQueCORE0.389F1 Score4May 29, 2026