deepseek-v4.1IMAGE
V4.1 Flash 1017 在 ExploitGYM 上与 GLM-5.3 对比
作者因官方 HF 卡未公布 Cyber/ExploitGYM 成绩,自行测试 V4.1 Flash 1017 并与 GLM-5.3 对比,怀疑 DS 未必强于 GLM。
Norsyx
@norsyx9 天前收录原推发布于 2026.10.23

Norsyx @norsyx原推发布于 2026.10.23
Benchmarking DeepSeek v4.1 Flash 1017 on Cyber/ExploitGYM since they didn't publish it on their HF card and comparing that with GLM-5.3 (since I don't believe DS is better than GLM)
x.com/norsyx/status/2113426336392081547采集于 2026.10.23 12:05