ResearchTasksCategorizationCategorizationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedFormalRx (test)FormalRx-8B64.4Accuracy11Jul 7, 2026LaMP-2N Cold-startPersonaAgent75.6Accuracy4May 29, 2026