ResearchTasksGroup Booking with failures (Grand Rollback)Group Booking with failures (Grand Rollback)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedτ2-bench+ / REALM-bench+ P14 v1 (test)RAC2Result Success Rate4May 6, 2026