ResearchTasksMultilingual EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTAXI1500MACRO75.7HLFR56May 13, 2026SIB200MACRO88.9HLFR56May 13, 2026GSM8K, IFEval, MMLU AggregateRA-MoE40.9Average Score15May 28, 2026ABBSYNDATA7.12Accuracy8May 12, 2026In-House Multilingual Datasets SEA Average 1.0GPT-5-Thinking90.15en Score8Feb 26, 2026