ResearchTasksQuality ScoringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSecurity ScenarioCASTER96.2Average Score15Feb 26, 2026Science ScenarioCASTER97.6Avg. Score15Feb 26, 2026Data ScenarioCASTER84.6Average Score15Feb 26, 2026Software ScenarioForce Strong100Average Score15Feb 26, 2026PANDABENCH (Hard set)PANDA0.36SRCC9Apr 14, 2026