ResearchTasksFailure FlippingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGSMPlusDoVer0.49Trial Success Rate1Feb 26, 2026GAIA Level-1DoVer27.5Trial Success Rate1Feb 26, 2026WW-GAIADoVer17.6Trial Success Rate1Feb 26, 2026WW-ABDoVer17.6Trial Success Rate1Feb 26, 2026