ResearchDatasetsLongSeALFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-hop Question AnsweringLongSeal15.35EM50Agentic SearchLongSeAL13.5String-F114Long-context reasoningLongSeal64.96Accuracy10