ResearchTasksannotationsannotationsFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedVerus-Bench full 150 tasksIDS149Pass Count4May 25, 2026DafnyBench 100 hardest tasksIDS88Pass Count4May 25, 2026