ResearchDatasetsAIReg-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHuman-Model AgreementAIReg-Bench0.863Quadratic Weighted Kappa10Regulatory reasoning and claim validationAIReg-Bench N=120 systems75.9Accuracy2