ResearchTasksMultiple Choice QuestioningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSafetyBench English (test)Safety Game (SG)60.13Accuracy35Jun 2, 2026RS-Neg MCQ (test)NeFo65.73Object Accuracy20Jun 19, 2026SemEval Task 7 Track 2 MCQ 2026 (Official results)Best-performing system on the leaderboard96.78Accuracy2May 25, 2026
SemEval Task 7 Track 2 MCQ 2026 (Official results)Best-performing system on the leaderboard96.78Accuracy2May 25, 2026