ResearchTasksExpert-Iteration RLVRExpert-Iteration RLVRFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMedQA, HEAD-QA, ARC-C, and CaseHOLDCSA4Pathwise Clean Score10May 21, 2026