ResearchTasksLLM Utility EvaluationLLM Utility EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLIMA original and rewritten variants (fine-tuning)CBBR77.6ARC-E Accuracy20May 20, 2026