ResearchTasksMulti-label Value ClassificationMulti-label Value ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGemini-annotated N=4,000 (test)XLM-RoBERTa-large0.752Self-direction Score1Jun 11, 2026