Inference Index
All datasets
Directory · Datasets · Evaluation
Evaluation

MMLU-Pro (test set)

The evaluation data behind MMLU-Pro. Use it to benchmark new models on expert knowledge.

Size
12K questions
Format
jsonl
License
MIT
Maintainer
TIGER-Lab

What it\u2019s for

The evaluation data behind MMLU-Pro. Use it to benchmark new models on expert knowledge.