ResearchTasksDialogue Commonsense ReasoningDialogue Commonsense ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCICERO v2 (test)TEAM93.25Accuracy4Feb 26, 2026CICERO v1 (test)Score88.04Accuracy4Feb 26, 2026