Global MMLU: Results as Published

Global MMLU is a multilingual copy of the MMLU exam questions, with coverage across 42 languages. The questions were machine-translated, then reviewed by compensated professional annotators and community annotators, and a subset is labeled culturally sensitive or culturally agnostic. The dataset card's lite release is balanced, with 200 culturally agnostic and 200 culturally sensitive samples per language, and it includes human translations for 15 languages. The paper reports accuracy, including average accuracy across languages.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.