ResearchTasksCompliance ClassificationCompliance ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCompliVision Average across 3 Domains (test)LLaVA-COT63.58Macro F116May 25, 2026Compliance domain (test)Oracle100Accuracy13Mar 18, 2026