Benchmark
WMT24++
language
text
多语言
WMT24++ is a comprehensive multilingual machine translation benchmark that expands the WMT24 dataset to cover 55 languages and dialects. It includes human-written references and post-edits across four domains (literary, news, social, and speech) to evaluate machine translation systems and large language models across diverse linguistic contexts.
语言EN
满分1
参评模型8
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Gemma 3 27B | 53.4 | 来源 ↗ | |
| 2 | Gemma 3 12B | 51.6 | 来源 ↗ | |
| 3 | Gemma 3n E4B Instructed | 50.1 | 来源 ↗ | |
| 4 | Gemma 3n E4B Instructed LiteRT Preview | 50.1 | 来源 ↗ | |
| 5 | Gemma 3 4B | 46.8 | 来源 ↗ | |
| 6 | Gemma 3n E2B Instructed | 42.7 | 来源 ↗ | |
| 7 | Gemma 3n E2B Instructed LiteRT (Preview) | 42.7 | 来源 ↗ | |
| 8 | Gemma 3 1B | 35.9 | 来源 ↗ |