ResearchTasksLogical Reasoning OversightLogical Reasoning OversightFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGGCBlack100AUC18Jun 4, 2026MALLSPipeline 10.967AUC18Jun 4, 2026FOLIOPipeline 195.3AUC18Jun 4, 2026