Benchmark
MEGA XStoryCloze
reasoning
language
text
多语言
XStoryCloze as part of the MEGA benchmark suite. A cross-lingual story completion task that consists of professionally translated versions of the English StoryCloze dataset to 10 non-English languages. Requires models to predict the correct ending for a given four-sentence story, evaluating commonsense reasoning and narrative understanding.
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 | 82.8 | 来源 ↗ |
| 2 | Phi-3.5-mini-instruct | Microsoft | 73.5 | 来源 ↗ |