{
 "id": "dia-bench/DIA-Bench",
 "owner": "dia-bench",
 "name": "DIA-Bench",
 "downloads": 173,
 "likes": 0,
 "last_modified": "2025-01-17T14:03:23.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@INPROCEEDINGS{diabench,\n  author={Tihanyi, Norbert and Bisztray, Tamas and Dubniczky, Richard A. and Toth, Rebeka and Borsos, Bertalan and Cherif, Bilel and Jain, Ridhi and Muzsai, Lajos and Ferrag, Mohamed Amine and Marinelli, Ryan and Cordeiro, Lucas C. and Debbah, Merouane and Mavroeidis, Vasileios and Jøsang, Audun},\n  booktitle={2024 IEEE International Conference on Big Data (BigData)}, \n  title={Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence}, \n  year={2024},\n  pages={3313-3321},\n  keywords={Measurement;Adaptation models;Computational modeling;Benchmark testing;Reliability engineering;Mathematical models;Data models;Reliability;Problem-solving;Computer security;Artificial Intelligence;Large Language Models;Dynamic Benchmarking;Performance Metrics;Reliability},\n  doi={10.1109/BigData62323.2024.10825051}}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "c3d4f495d6662291b7cfc8d08d7b23d0717dcc85",
 "stated_evidence": "https://huggingface.co/datasets/dia-bench/DIA-Bench/blob/c3d4f495d6662291b7cfc8d08d7b23d0717dcc85/README.md",
 "file_evidence": "https://huggingface.co/datasets/dia-bench/DIA-Bench/tree/c3d4f495d6662291b7cfc8d08d7b23d0717dcc85",
 "card_nc": false
}