ResearchDatasetsclawevalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic EvaluationClawEval 042470.4Pass^3 Score7AgenticClawEval64.56Score7Agent tool-useClawEval 114 T-family tasks37.7p@14Agentic workflow auditingclaweval53.3SLA Compliance Audit Score (zh)2