ResearchTasksMultilingual LLM-as-a-JudgeFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU-ProXSEMJ60.27Accuracy5Jun 9, 2026BelebeleSEMJ63.92Accuracy5Jun 9, 2026XStoryClozeSEMJ78.84Accuracy5Jun 9, 2026Wino-X-MtSEMJ50.44Accuracy5Jun 9, 2026Wino-XSEMJ72.92Accuracy5Jun 9, 2026XCOPASEMJ63.36Accuracy5Jun 9, 2026