HAE-RAE
labScores
1 product on the map — 1 closed.
Openness
2 high confidence- license
- cc-by-nd-4.0 (card metadata and API tag)
- access
- public (ungated on the Hub)
- dataset_card
- present (card describes the benchmark, its splits and statistics, and links the paper)
The questions download freely, but the license forbids distributing changed versions, so a translation or a derived benchmark cannot be shared. The card and paper describe how the questions were collected.
- https://huggingface.co/api/datasets/HAERAE-HUB/KMMLU recorded 2026-11-11
API JSON: "gated":false; tag license:cc-by-nd-4.0.
- https://huggingface.co/datasets/HAERAE-HUB/KMMLU/raw/main/README.md recorded 2026-11-11
Card metadata "license: cc-by-nd-4.0"; body: "KMMLU is collected from original Korean exams"; statistics table "Train 208,522", "Validation 225", "Test 35,030".
Adoption
3 high confidenceHugging Face downloads of the Hub repository over the trailing month. A download count does not say who downloaded, and evaluation harnesses can fetch a benchmark repeatedly, so the figure is a rough measure of use, not a count of users or organizations.
- https://huggingface.co/api/datasets/HAERAE-HUB/KMMLU recorded 2026-11-11
"downloads":11793 for HAERAE-HUB/KMMLU.
Capability
5 medium confidenceIn its one target language, KMMLU's test has more than sixty-four hundred items that count toward depth. An item count says how much a set can test, not how precisely it ranks models.
- https://arxiv.org/abs/2402.11548 recorded 2026-11-11
Abstract: "We propose KMMLU, a new Korean benchmark with 35,030 expert-level multiple-choice questions across 45 subjects ranging from humanities to STEM"; "KMMLU is collected from original Korean exams".
- https://arxiv.org/pdf/2402.11548 recorded 2026-11-11
"all sourced from original Korean exams without any translated content"; "We predominantly source the questions from Korean License Tests"; "This filtering reduces the dataset by 34% to 243,777 questions".
- https://datasets-server.huggingface.co/size?dataset=HAERAE-HUB/KMMLU recorded 2026-11-11
The Hub's row counts over 45 subject configurations, complete ("partial":false): test 35,030, dev 225 and train 208,522 rows, 243,777 in all.