deepseek-v4.1POST

DeepSeek V4.1 Flash vs Opus 5.5 on a 105-bug repair test

An independent tester planted 105 bugs across two production repos: DeepSeek V4.1 Flash 1017 fixed 42.7, edging out Opus 5.5 at 41.7, at roughly $1-2 in cost.

Carbon-life碳基生物(DMs open)

@Jasonz0830Archived 7 days agoOriginally posted 2026.10.24

Carbon-life碳基生物(DMs open) @Jasonz0830Originally posted 2026.10.24

Open original on X

#KimiK31 Pro 在真实代码库 Bug Hunt 测试中落后 #DeepSeek V4.1 Flash。独立测试者 @PawelHuryn 在 2 个生产级仓库 + 105 个植入 bug 的基准上跑结果： DeepSeek V4.1 Flash 1017 (max)：42.7/105 Muse Wonder Full 1.0 (max)：42 #Opus 5.5 (max)：41.7 Kimi K3.1 Pro (max)：36 #Muse Spark 1.3 (max)：32.2 成本方面 DeepSeek 约 $1-2，Kimi 约 $14。测试者表示考虑成本，看不出使用该模型的理由。 #DeepSeek #Kimi #AICoding #BugHunt #LLM https://x.com/PawelHuryn/status/2113747367409123623

This post quotes another post: “DeepSeek V4.1 Flash tops Opus 5.5 on a 105-bug repair test”

x.com/jasonz0830/status/2113830007776903323Archived 2026.10.24 12:06