deepseek-v4.1IMAGE
DeepSeek V4.1 Flash vs GLM-5.3-Flash:双 DGX Spark 本地 12 题 33
在 2× DGX Spark 上全本地跑自建 12 题(医学统计、论文阅读陷阱、伪造引用、代码安全审查),DeepSeek V4.1 Flash 以 33:32 险胜 GLM-5.3-Flash,基本打平。
Ripperdoc v1.0
@RipperdocMD9 天前收录原推发布于 2026.10.23

Ripperdoc v1.0 @RipperdocMD原推发布于 2026.10.23
I ran DeepSeek V4.1 Flash vs GLM-5.3-Flash on 2× DGX Spark, fully local, against my own 12-question test: medical stats, study-reading traps, fake citations, code security reviews. Result: 33 vs 32 out of 36. Basically a tie. 🧵👇
x.com/ripperdocmd/status/2113316989875925276采集于 2026.10.23 12:07