ResearchDatasetsAPT-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAtomic Perception of TransitionsAPT-BENCH (test)53.4Recall12APT chain enumerationAPT-BENCH (test)14Recall8ToolAPT-Bench65.8Accuracy6MathAPT-Bench70.5Accuracy6Deep ResearchAPT-Bench40.5Accuracy6CodeAPT-Bench41.9Accuracy6