ResearchTasksEarly-stopping budget estimationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSearch-R1, Sokoban, SWE-bench, and Warehouse Aggregate (test)Claude Opus 4.72.2False-Abort Rate5Jun 2, 2026
Search-R1, Sokoban, SWE-bench, and Warehouse Aggregate (test)Claude Opus 4.72.2False-Abort Rate5Jun 2, 2026