Skip to content

Dataset · mhardalov

EXAMS multilingual school exam questions

mhardalov/exams

A benchmark of over 24,000 school exam questions across 16 languages for model evaluation.

What's inside

It contains over 24,000 high-quality questions from final high school exams across 24 subjects, including natural and social sciences. The data covers 16 languages from 8 language families, including Arabic, Bulgarian, German, Spanish, French, and Croatian. The total repository size in metadata is listed between 100 thousand and 1 million records.

What you can do with it

  • Evaluate the performance of multilingual LLMs on question-answering tasks
  • Test cross-lingual knowledge transfer across school subjects
  • Fine-tune models for educational systems and automated grading
Tasks
Question answering
Languages
Arabic, Bulgarian, German, Spanish, French, Croatian, Hungarian, Italian and 4 more
Size
100K–1M rows
Downloads this month
7.4K
Likes
40

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("mhardalov/exams")