ResearchDatasetsCUREMED-BENCHFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultilingual Medical ReasoningCUREMED-BENCH (test)94.96Consistency33Multilingual Medical ReasoningCUREMED-BENCH averaged across 13 languages93.43Language Consistency5