ResearchDatasetsArabic BenchmarksArabic BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultitask Language EvaluationArabic Benchmarks (COPA-ar, HellaSwag-ar, ArabicMMLU)69.7COPA-ar7