language benchmark
Multilingual MMLU Leaderboard
Multilingual MMLU is a multilingual benchmark based on MMLU-ProX, covering 29 typologically diverse languages with 11,829 identical questions per language.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
Multilingual MMLU Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score80.70% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score74.20% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score70.60% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score65.20% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelMI | Score49.30% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
Multilingual MMLU Highlights
The leading models and scores on this benchmark.
Multilingual MMLU Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Multilingual MMLU
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Multilingual MMLU?
What Multilingual MMLU measures and how its scores work.
Multilingual MMLU is a benchmark for evaluating large language models across 29 languages using challenging, reasoning-focused questions with 10 answer choices.
It measures large language models' reasoning capabilities across linguistic and cultural boundaries.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Multilingual MMLU
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Multilingual MMLU.
Which model scores highest on Multilingual MMLU?
o3-mini is currently ranked first with 80.70%.
What are the top three models on Multilingual MMLU?
The current leaders are o3-mini (80.70%), Ministral 3 (14B Base 2512) (74.20%), and Ministral 3 (8B Base 2512) (70.60%).
Which Multilingual MMLU model has the lowest official input price?
Phi 4 Mini has the lowest matched official input price at $0.08 input / $0.30 output per 1M tokens.
Which models are fastest among Multilingual MMLU results?
The fastest matched records are o3-mini (115.00 tok/s via Azure).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.