[分享发现] NIST 的测试要比各家自己吹的口径靠谱吧
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
caisi - 钛刻 - 科技风向旗 - 深度刻画技术趋势,引领数字未来 - 钛刻科技 | TCTI.cn - 钛刻 (TCTI.cn) 为您提供最前沿的硬核科技资讯、深度评测和未来技术趋势分析。
共 13 篇相关文章
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro
人工智能标准与创新中心(CAISI)近日完成了对开源人工智能模型 DeepSeek V4 Pro的全面评估。报告指出,尽管DeepSeek V4展示了卓越的性能,并在多项指标上大幅领先于国内同类模型,但其综合能力相较于美国最前沿技术仍有约8个月的代差。 CAISI的IRT(项目反