Multilingual MMLU (Meta)
Llama 3.1-405B 83.2% leads since Nov 2024 Only in system cards Models answer MMLU questions machine-translated into German, French, Italian, Portuguese, Hindi, Spanish and Thai, 5-shot.
In-house Meta translation made with Google Translate. It differs from OpenAI's MMMLU.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
Llama 3.1-405B leads with 83.2% among models released by Jul 2024
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Jul 2024, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Llama 3.1-405B 83.2%
- 2 Llama 3.1-70B 78.2%
- 3 Llama 3.1-8B 58.6%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Llama 3.1-405B | 83.2% | Nov 2024 | Model card | |
| 2 | Llama 3.1-70B | 78.2% | Nov 2024 | Model card | |
| 3 | Llama 3.1-8B | 58.6% | Nov 2024 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
6 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 23 Nov 2024 | Llama 3.1-8B technical report | 58.6 | Multilingual MMLU (internal, 7 languages, 5-shot), post-trained (Table 20) | Capabilities |
| 23 Nov 2024 | Llama 3.1-70B technical report | 78.2 | Multilingual MMLU (internal, 7 languages, 5-shot), post-trained (Table 20) | Capabilities |
| 23 Nov 2024 | Llama 3.1-405B technical report | 83.2 | Multilingual MMLU (internal, 7 languages, 5-shot), post-trained (Table 20) | Capabilities |
| 23 Jul 2024 | Llama 3.1-8B model card | MMLU (5-shot, macro_avg/acc) per language with no overall, instruction tuned (Multilingual benchmarks table): Portuguese 62.12, Spanish 62.45, Italian 61.63, German 60.59, French 62.34, Hindi 50.88, Thai 50.32 | Capabilities | |
| 23 Jul 2024 | Llama 3.1-70B model card | MMLU (5-shot, macro_avg/acc) per language with no overall, instruction tuned (Multilingual benchmarks table): Portuguese 80.13, Spanish 80.05, Italian 80.4, German 79.27, French 79.82, Hindi 74.52, Thai 72.95 | Capabilities | |
| 23 Jul 2024 | Llama 3.1-405B model card | MMLU (5-shot, macro_avg/acc) per language with no overall, instruction tuned (Multilingual benchmarks table): Portuguese 84.95, Spanish 85.08, Italian 85.04, German 84.36, French 84.66, Hindi 80.31, Thai 78.21 | Capabilities |
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5% - MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87% - CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7% - Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy.
Inkling 88.7% - MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%