Benchmark
Global-MMLU
general
language
reasoning
text
多语言
A comprehensive multilingual benchmark covering 42 languages that addresses cultural and linguistic biases in evaluation, with improved translation quality and culturally sensitive question subsets.
语言EN
满分1
参评模型4
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Gemma 3n E4B Instructed | 60.3 | 来源 ↗ | |
| 2 | Gemma 3n E4B Instructed LiteRT Preview | 60.3 | 来源 ↗ | |
| 3 | Gemma 3n E2B Instructed | 55.1 | 来源 ↗ | |
| 4 | Gemma 3n E2B Instructed LiteRT (Preview) | 55.1 | 来源 ↗ |