ResearchTasksDeontic ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedDeonticBench USCIS-AAOGPT-5.281.9Macro F130Jun 4, 2026DeonticBench SARA-BinQwen3.5-397B90.6Macro F130Jun 4, 2026DeonticBench AirlineGPT-5.236.3Accuracy30Jun 4, 2026DeonticBench SARA-NumQwen3.5-397B77.1Accuracy30Jun 4, 2026