ResearchTasksAgreement with process human labelsFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCUAVerifierBench Browserbase OM2WUniversal Verifier (UV)78Accuracy8Apr 9, 2026CUAVerifierBench (Internal Dataset (n=140))Universal Verifier (UV)81Accuracy8Apr 9, 2026