reasoning benchmark
French MMLU
French version of MMLU-Pro, a multilingual benchmark for evaluating language models' cross-lingual reasoning capabilities across 14 diverse domains including mathematics, physics, chemistry, law, engineering, psychology, and health.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
French MMLU leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 57.5% | 100.0% | 1 | C |
French MMLU highlights
The top published results on this benchmark's own scale.
What is French MMLU?
Definition and scoring fields from the benchmark registry.
French version of MMLU-Pro, a multilingual benchmark for evaluating language models' cross-lingual reasoning capabilities across 14 diverse domains including mathematics, physics, chemistry, law, engineering, psychology, and health.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- French MMLU
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- french-mmlu|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about French MMLU.
Which model scores highest on French MMLU?
Ministral 8B Instruct is currently ranked first with 57.5%.
What does French MMLU measure?
French version of MMLU-Pro, a multilingual benchmark for evaluating language models' cross-lingual reasoning capabilities across 14 diverse domains including mathematics, physics, chemistry, law, engineering, psychology, and health.
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.