LLM Stats (Multilingual MMLU): leaderboard
MMLU translated into multiple languages testing broad academic knowledge retention across non-English languages.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 Mini | 80.7 | #272 |
| 2 | Phi-4 Mini Instruct | 49.3 | #1245 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-multilingual-mmlu · How It Works · Data refreshed daily, snapshot 2026-10-20.