ResearchTasksZero-shot Downstream TasksZero-shot Downstream TasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedARC-C, ARC-E, HellaSwag, PIQA, and WinoGrandeFP1674.35Downstream Average10Jun 4, 2026