ResearchTasksBudget recipe evaluationBudget recipe evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLinux L40S 24hgreedy_winner_10min_s1595.465Mean Score3Jun 5, 2026Windows 24hpredeclared_control_c1095.093Sample Mean3Jun 5, 2026