ResearchTasksPrompt SelectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSelected tasks APE-generated prompt pools APE design (test)TRIPLE-CLST1.41Averaged Performance Rank44Feb 26, 2026Perturbation-100 (test)Risk-Cos76Top-1 Hit4Mar 23, 2026
Selected tasks APE-generated prompt pools APE design (test)TRIPLE-CLST1.41Averaged Performance Rank44Feb 26, 2026