Eval

When this dataset fits

Eval is a Korean Instruction Tuning Dataset from Hugging Face. It is a scoring set. Do not train on the test items. License label MIT still needs review. Size text is “178KB”, copied from the host.

Task / category

Text · Text · benchmark

Language

Korean

Format · Size

Text · 178KB (522 items)

License

MIT(Catalog hint — re-check original) · License document

Source & original link

Hugging Face · Original dataset link(Verified)

Verification status

Source: Verified · License: Needs review · Last checked: 2026-09-03

Eval: Korean Instruction Tuning Dataset from Hugging Face. License MIT. Open the original link to download.

Eval (2024). Hugging Face. license label: MIT catalog commercial mark: allowed Original: https://huggingface.co/datasets/HAERAE-HUB/K2-Eval. GearDel catalog: https://geardel.com/en/datasets/k2-eval. 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.

• HAE-RAE Bench 1.1Korean LLM Benchmark Dataset · Hugging FaceViewLicense labels differ (MIT vs CC BY-NC-ND 4.0). Commercial marks differ (Commercial use allowed (catalog) vs Commercial use may be conditional). Size text differs (178KB vs 2.9MB). Those strings are copied from the hosts.
• CLIcK (Cultural & Legal Knowledge)Korean LLM Benchmark Dataset · GitHubViewLicense labels differ (MIT vs License unknown). Providers differ (Hugging Face vs GitHub). Size text differs (178KB vs 5.5MB). Those strings are copied from the hosts.
• KoSafetyBenchKorean LLM Benchmark Dataset · Hugging FaceViewLicense labels differ (MIT vs CC BY 4.0). Size text differs (178KB vs 15MB). Those strings are copied from the hosts. Catalog years differ (2024 vs 2025).
• HAE-RAE Bench 2.0Korean LLM Benchmark Dataset · Hugging FaceViewSize text differs (178KB vs 1.0MB). Those strings are copied from the hosts.