deepseek-v4.1IMAGE

DeepSeek V4.1 Flash 1017 fixes the hardest bug on the final round, matching Opus 5.5

In a legacy-code bug-fix benchmark, DeepSeek V4.1 Flash 1017 solved the hardest bug only on the last round — the same as Opus 5.5 — despite being a small flash model.

Yanchy Shum

@yanchyshumArchived 3 days agoOriginally posted 2026.10.26

DeepSeek V4.1 Flash 1017 fixes the hardest bug on the final round, matching Opus 5.5 (image 1 of 3)

DeepSeek V4.1 Flash 1017 fixes the hardest bug on the final round, matching Opus 5.5 (image 2 of 3)

DeepSeek V4.1 Flash 1017 fixes the hardest bug on the final round, matching Opus 5.5 (image 3 of 3)

Yanchy Shum @yanchyshumOriginally posted 2026.10.26

Open original on X

刚看到词元的屎山代码修复测评王者 BUG deepseek v4.1 flash 1017 在最后一轮成功拿下！！要知道 opus 5.5 也仅仅在最后一轮才拿下，而且 deepseek 只是一个 flash 的小模型！！！梁圣牛逼🤓🤓

x.com/yanchyshum/status/2114530718269473043Archived 2026.10.26 12:03