GAIA：通用 AI 助手基准

Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, Thomas Scialom

数据集 2023 原文 2023-11-21 NeurIPS 2023 (Datasets & Benchmarks) arXiv:2311.12983 收录 2026-09-06 benchmarkgeneral-assistantevaluation

摘要

466 个需要推理、多模态理解、网页浏览与工具使用的问题基准——人类轻松可得高分，却能让最强 AI 系统频频失手。

引用本文条目

GB/T 7714-2015

Grégoire Mialon, Clémentine Fourrier, Craig Swift, et al. GAIA: A Benchmark for General AI Assistants[EB/OL]. NeurIPS 2023 (Datasets & Benchmarks), 2023(2023-11-21)[2026-11-01]. https://arxiv.org/abs/2311.12983.

BibTeX

@misc{mialon2023,
  author = {Grégoire Mialon and Clémentine Fourrier and Craig Swift and Thomas Wolf and Yann LeCun and Thomas Scialom},
  title = {GAIA: A Benchmark for General AI Assistants},
  year = {2023},
  organization = {NeurIPS 2023 (Datasets & Benchmarks)},
  howpublished = {\url{https://arxiv.org/abs/2311.12983}},
}

查看原文 ↗

本条目为「智联观察」资料库收录，引用时请注明来源与本页链接。