Global-MMLU-Lite
knowledgeVerified
A balanced collection of culturally sensitive and culturally agnostic MMLU tasks designed for efficient evaluation of multilingual models in 15 languages (including English).
Published: 2025
Score Range: 0-100
Top Score: 86.5
Global-MMLU-Lite Leaderboard
| Rank | Model | Provider | Score | Parameters | Released | Type |
|---|---|---|---|---|---|---|
| 1 | Gemini 2.0 Pro | 86.5 | 2025-02-05 | Multimodal | ||
| 2 | Gemini 2.5 Flash-Lite | 84.5 | 2025-06-17 | Multimodal | ||
| 3 | Gemini 2.0 Flash | 83.4 | 2025-02-25 | Multimodal | ||
| 4 | Gemini 2.0 Flash-Lite | 78.2 | 2025-02-25 | Multimodal |
About Global-MMLU-Lite
Methodology
Global-MMLU-Lite evaluates model performance using a standardized scoring methodology. Scores are reported on a scale of 0 to 100, where higher scores indicate better performance. For detailed information about the scoring system and methodology, please refer to the original paper.
Publication
This benchmark was published in 2025.Technical Paper