ResearchTasksSource Task PerformanceSource Task PerformanceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPoisoned Apple simple_5x5Source100Critical State Safety Rate4Apr 13, 2026Frozen Lake standard_4x4Source100Critical State Safety Rate4Apr 13, 2026