ResearchDatasetsAgentic-WideFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic SearchAgentic-Wide TaskCraft (test)90.1Accuracy4Agentic SearchAgentic-Wide WebWalkerQA (test)62.5Accuracy4Agentic SearchAgentic-Wide XBench (test)74.19Accuracy4