Benchmark
MEGA MLQA
language
reasoning
text
多语言
MLQA as part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite. A multi-way aligned extractive QA evaluation benchmark for cross-lingual question answering across 7 languages (English, Arabic, German, Spanish, Hindi, Vietnamese, and Simplified Chinese) with over 12K QA instances in English and 5K in each other language.
语言EN
满分1
参评模型2
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Phi-3.5-MoE-instruct | Microsoft | 65.3 | 来源 ↗ |
| 2 | Phi-3.5-mini-instruct | Microsoft | 61.7 | 来源 ↗ |