MMMLU: leaderboard
Multilingual Massive Multitask Language Understanding, an MMLU test-set translation across 14 non-English languages for multilingual knowledge and reasoning.
Metric: Score (%). Source: huggingface.co. Source: benchmarklist.com. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B | 88.4 | #200 |
| 2 | Gemma 4 26B A4B | 86.3 | #358 |
| 3 | Gemma 4 E4B | 76.6 | #767 |
| 4 | Gemma 4 E2B | 67.4 | #1070 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmmlu · How It Works · Data refreshed daily, snapshot 2026-10-20.