{
 "id": "cs-552-2026-databand/general_knowledge_benchmark",
 "owner": "cs-552-2026-databand",
 "name": "general_knowledge_benchmark",
 "downloads": 28,
 "likes": 0,
 "last_modified": "2026-06-09T11:28:10.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "text-classification"
 ],
 "citation": "MMLU-Pro:\nWang, Y., Ma, X., Zhang, G., and others. 2024. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark. arXiv:2406.01574. https://arxiv.org/abs/2406.01574\n\nMMLU-Redux:\nGema, A. P., Leang, J. O. J., Hong, G., and others. 2025. Are We Done with MMLU? NAACL 2025. https://arxiv.org/abs/2406.04127\n\nSuperGPQA:\nDu, X., Yao, Y., Ma, K., and others. 2025. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines. arXiv:2502.14739. https://arxiv.org/abs/2502.14739",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "dcfc9570ca3d530664784d03b19605f6ccb83f3c",
 "stated_evidence": "https://huggingface.co/datasets/cs-552-2026-databand/general_knowledge_benchmark/blob/dcfc9570ca3d530664784d03b19605f6ccb83f3c/README.md",
 "file_evidence": "https://huggingface.co/datasets/cs-552-2026-databand/general_knowledge_benchmark/tree/dcfc9570ca3d530664784d03b19605f6ccb83f3c",
 "card_nc": false
}