风险评测 · 技术报告
CAISI Evaluation of DeepSeek V4 Pro
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节;尚未完成逐章节审计。
研究速读
NUWA 解读:落后时间是模型化历史总结,不代表每任务均落后。
研究问题
独立选择的评测集合如何改变DeepSeek V4 Pro能力图景?
研究设计与假设
九基准覆盖五领域含两个保留集,1PL IRT按领域内基准及领域等权拟合。
来源发现
报告在所选集合估计综合能力约落后八个月。
复现GPQA-Diamond检查推理配置,并注明SWE-bench提示框架预算差异。
NUWA 解读
NUWA 解读:落后时间是模型化历史总结,不代表每任务均落后。
局限与相反证据
CTF含IRT推补,PortBench连续计分;成本仅覆盖七个合格基准及共同解出任务。
研究与决策意义
模型建议:综合结论旁保留逐基准证据、IRT假设与排除规则。
精确来源位置
- CAISI Evaluation of DeepSeek V4 Pro · Capability ResultsSelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
- CAISI Evaluation of DeepSeek V4 Pro · BenchmarksSelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
- CAISI Evaluation of DeepSeek V4 Pro · Capability Lag MeasurementSelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
- CAISI Evaluation of DeepSeek V4 Pro · Comparison of DeepSeek and CAISI EvaluationsSelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
- CAISI Evaluation of DeepSeek V4 Pro · DeepSeek V4 Costs Less Than Other Models Of Similar CapabilitySelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
- CAISI Evaluation of DeepSeek V4 Pro · AppendixSelected original resource https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro; sha256:37f75aab5640e04d198b94a0ca57704b06d7823caeeb05c4280c8fc461b00623; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
评测协议
引用与复用
引用研究发现时请引用原始出版物;引用 NUWA 的整理与解释时,单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{caisi-deepseek-v4-report,
title = {CAISI Evaluation of DeepSeek V4 Pro},
url = {https://www.nist.gov/news-events/news/2026/05/caisi-evaluation-deepseek-v4-pro},
year = {2026},
date = {2026-05-01},
version = {1 May 2026},
note = {1 May 2026}
}
NUWA 记录 · BibTeX
@misc{caisi-deepseek-v4-report-nuwa,
title = {CAISI Evaluation of DeepSeek V4 Pro — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/caisi-deepseek-v4-report/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--caisi-deepseek-v4-report.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--caisi-deepseek-v4-report.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] CAISI Evaluation of DeepSeek V4 Pro. 2026-05-01. 1 May 2026 ; Report masthead and stated evaluation methodology; Capability Results; Benchmarks