ResearchTasksRelevance ScoringRelevance ScoringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPASTA AI Compliance Evaluation Dataset (Expert Evaluation)PASTA0.661ICC2Feb 26, 2026Expert Consensus (test)PASTA0.761Spearman Rho1Feb 26, 2026