KoCommonGEN v2

When this dataset fits

KoCommonGEN v2 is a Korean LLM Benchmark Dataset from Hugging Face. It is a scoring set. Do not train on the test items. The catalog does not claim a license. Size text is “183KB”, copied from the host.

Task / category

Text · Text · benchmark, commonsense, generation

Language

Korean

Format · Size

Text · 183KB (852 public samples)

License

License unknown(No confirmed license in catalog)

Source & original link

Hugging Face · Original dataset link(Verified)

Verification status

Source: Verified · License: Unknown · Last checked: 2026-09-03

KoCommonGEN v2: Korean LLM Benchmark Dataset from Hugging Face. License license on original source. Open the original link to download.

KoCommonGEN v2 (2024). Hugging Face. license label: License unknown catalog commercial mark: conditional Original: https://huggingface.co/datasets/nlpai-lab/ko_commongen_v2. GearDel catalog: https://geardel.com/en/datasets/ko-commongen-v2. Last checked: 2026-09-03. Author names are not stored in the GearDel catalog and are not invented here.

Differences below use catalog fields only: license, commercial mark, provider, size text, and year.

• HRMCRKorean LLM Benchmark Dataset · Hugging FaceViewLicense labels differ (License unknown vs Apache 2.0). Commercial marks differ (Commercial use may be conditional vs Commercial use allowed (catalog)). Size text differs (183KB vs 106KB). Those strings are copied from the hosts.
• Ko-PIQAKorean QA Dataset · Hugging FaceViewSize text differs (183KB vs 204KB). Those strings are copied from the hosts. Catalog years differ (2024 vs 2025).
• KoBESTKorean LLM Benchmark Dataset · Hugging FaceViewLicense labels differ (License unknown vs CC BY-SA 4.0). Commercial marks differ (Commercial use may be conditional vs Commercial use allowed (catalog)). Size text differs (183KB vs 5.1MB). Those strings are copied from the hosts.
• KoSafetyBenchKorean LLM Benchmark Dataset · Hugging FaceViewLicense labels differ (License unknown vs CC BY 4.0). Commercial marks differ (Commercial use may be conditional vs Commercial use allowed (catalog)). Size text differs (183KB vs 15MB). Those strings are copied from the hosts.