List your company

ResearchFormerly WizWand

DeonticBench

Benchmarks

TaskDatasetSOTA resultTrendResults

Deontic Reasoning

DeonticBench USCIS-AAO

81.9Macro F1

30

Deontic Reasoning

DeonticBench SARA-Bin

90.6Macro F1

30

Deontic Reasoning

DeonticBench Airline

36.3Accuracy

30

Deontic Reasoning

DeonticBench SARA-Num

77.1Accuracy

30