ResearchTasksQuestion MiningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGMMLU common 30 languages (test)Qwen3-Embedding-0.6B11.3XSim Score7Mar 18, 2026GMMLU all 41 languages (test)Qwen3-Embedding-0.6B23.9XSim Score7Mar 18, 2026