Mmmlu
MMMLU (Multilingual MMLU) parity validation subset with 10 tasks per language across 15 languages (150 tasks total). Evaluates language models' subject knowledge and reasoning across multiple languages using multiple-choice questions covering 57 academic subjects.
- Domain
- agent-eval
- Published
- Nov 2025
Cite
Notes
Only stored in your browser.
FAQ
- What is Mmmlu?
- MMMLU (Multilingual MMLU) parity validation subset with 10 tasks per language across 15 languages (150 tasks total). Evaluates language models' subject knowledge and reasoning across multiple languages using multiple-choice questions covering 57 academic subjects.