新版不如旧版，这升级升了个寂寞 DeepSeek V4.1 Flash 1017，会计基准 DualBench100 只拿 82.2%，旧版 84.2% 榜… · @ai_fengshou · TwKit

@ai_fengshou

新版不如旧版，这升级升了个寂寞 DeepSeek V4.1 Flash 1017，会计基准 DualBench100 只拿 82.2%，旧版 84.2% 榜首 Gemini 4 Argon 91.1%，开放最强 GLM-5.3 Flash 88.1% 我部署模型前一定先看榜单，版本号真不是越大越强 https://www.businesswire.com/news/home/20261021130097/en/DeepSeeks-Latest-Update-Scores-Lower-on-Accounting-Work-as-Open-Models-Trail-on-Consistency-DualEntry-Benchmark-Finds

曝光 99 · 评论 1 · 点赞 2 · 书签 0