ResearchTasksSecure LLM Agent Task CompletionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAgentDojoProgent76.3Benign Utility9Jun 9, 2026ASBDRIFT78.75Benign Utility4Mar 27, 2026