Multilingual MMLU
MMLU-ProX is a comprehensive multilingual benchmark covering 29 typologically diverse languages, building upon MMLU-Pro. Each language version consists of 11,829 identical questions enabling direct cross-linguistic comparisons. The benchmark evaluates large language models' reasoning capabilities across linguistic and cultural boundaries through challenging, reasoning-focused questions with 10 answer choices.
o3-mini from OpenAI currently leads the Multilingual MMLU leaderboard with a score of 0.807 across 5 evaluated AI models.
o3-mini leads with 80.7%, followed by 
Ministral 3 (14B Base 2512) at 74.2% and Ministral 3 (8B Base 2512) at 70.6%.
Progress Over Time
Interactive timeline showing model performance evolution on Multilingual MMLU
Multilingual MMLU Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | OpenAI | — | — | — | ||
| 2 | Mistral AI | 14B | — | — | ||
| 3 | Mistral AI | 8B | — | — | ||
| 4 | Mistral AI | 3B | — | — | ||
| 5 |  Microsoft | 4B | — | — |
FAQ
Common questions about Multilingual MMLU.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions