Hugging Face dataset · #66

TIGER-Lab/MMLU-Pro

TIGER-Lab/MMLU-Pro is #66 among listed Hugging Face datasets, with 582 likes. MMLU-Pro dataset is a more robust and challenging massive multi-task understanding dataset tailored to more rigorously benchmark large language models' capabilities. This dataset contains 12K complex questions across various disciplines. |Github | 🏆Leaderboard | 📖Paper | 🚀…

Dataset
https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro
Author
TIGER-Lab (org)
Likes
582
Downloads (30 days)
255,088
License
mit
Size
10K<n<100K
Tasks
question-answering
Modalities
tabular, text
Gated
No
Created
2024-05-08
Last modified
2026-05-02
Snapshot
2026-10-21

Back to Hugging Face datasets · Methodology