ResearchTasksBudget recipe evaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLinux L40S 24hgreedy_winner_10min_s1595.465Mean Score3Jun 5, 2026Windows 24hpredeclared_control_c1095.093Sample Mean3Jun 5, 2026