math benchmark
MMLU French
French language variant of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. This multilingual version tests model performance in French.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
MMLU French leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 82.8% | 100.0% | 1 | C |
MMLU French highlights
The top published results on this benchmark's own scale.
What is MMLU French?
Definition and scoring fields from the benchmark registry.
French language variant of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. This multilingual version tests model performance in French.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMLU French
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmlu-french|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MMLU French.
Which model scores highest on MMLU French?
Mistral Large 2 is currently ranked first with 82.8%.
What does MMLU French measure?
French language variant of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. This multilingual version tests model performance in French.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.