ResearchDatasetsCAPTRACEBENCHFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic Task ExecutionCAPTRACEBENCH Easy 1.081.4Success Rate (SR)15Agentic Task ExecutionCAPTRACEBENCH Hard 1.044Success Rate (SR)12Agentic Task ExecutionCAPTRACEBENCH Medium 1.061.5Success Rate11