ModelRefs / Multilingual MMLU Methodology and Evidence
Multilingual MMLU Methodology and Evidence
MMLU translated across 26 languages by Cohere & contributors. Methodology, dataset provenance, and citation sources for Multilingual MMLU.
Overview
MMLU translated across 26 languages by Cohere & contributors.
How it is measured: Mean accuracy across languages.
How this benchmark is scored
| Category | reasoning |
|---|---|
| Maximum score | 100 % accuracy |
| Direction | Higher is better |
Primary source: https://huggingface.co/datasets/CohereForAI/Global-MMLU
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Multilingual MMLU Methodology and Evidence.
Frequently asked questions
What does the Multilingual MMLU benchmark measure?
MMLU translated across 26 languages by Cohere & contributors.
What is the methodology?
Mean accuracy across languages.