ResearchTasksSearch-Augmented ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSEARCHGEN-BENCH Search OverallGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO31.8Score12Jul 7, 2026SEARCHGEN-BENCH Search Set IIIGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO27.4Score12Jul 7, 2026SEARCHGEN-BENCH Search Set IIORACLE + Klein-4B-DPO33.9Score12Jul 7, 2026SEARCHGEN-BENCH Search Set IGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO34.1Score12Jul 7, 2026SEARCHGEN-BENCH NoSearchGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO56.9Score12Jul 7, 2026GAIA TextSAKE59L1 Accuracy9Feb 26, 2026
SEARCHGEN-BENCH Search OverallGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO31.8Score12Jul 7, 2026
SEARCHGEN-BENCH Search Set IIIGENERATOR-ADAPTIVE SEARCH (RFT-8B) + Klein-4B-DPO27.4Score12Jul 7, 2026