Dataset · henrikhoffmanndk
Multilingual benchmark: 50 First Facts
henrikhoffmanndk/50-first-facts
Multilingual benchmark of basic facts about 30 European countries for evaluating QA models.
What's inside
Contains 33,000 questions across 66 files in multiple languages (including bg, cs, da, de, el, en). Designed to check general factual knowledge known by an average adult resident of a country.
What you can do with it
- Benchmarking multilingual language models
- Evaluating QA systems on geographic and cultural knowledge
- Tasks
- Question answering
- Languages
- Bulgarian, Czech, Danish, German, Greek, English, Spanish, Estonian and 4 more
- Size
- 10K–100K rows
- Downloads this month
- 24.1K
- Likes
- 0
- Access
- on request on Hugging Face
How to load it
from datasets import load_dataset
ds = load_dataset("henrikhoffmanndk/50-first-facts")