ResearchTasksAnnotation AccuracyAnnotation AccuracyFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedDeepSeek-R1 Experiment 1Template-based100F1 Score (Ga)40Apr 10, 2026Experiment 1 (test)Template-based100F1 Score (Ga)40Apr 10, 2026