WHAT NEW IN X10.30 FRI

AI collections from X · 22 collections · 60,637 posts

gemini-4IMAGE

FrontierCode 2.0: DeepSeek V4.1 Flash hits 28.5%, ahead of Gemini 4 Argon at 25.7%

On AA's FrontierCode 2.0 engineering benchmark, DeepSeek V4.1 Flash leads open models at 28.5%, with the post comparing Gemini 4 Argon at 25.7% and GPT-6 Luna at 25.2%.

SuSu_酥酥👅
@NFT_ChenArchived 16 hours agoOriginally posted 2026.10.28
FrontierCode 2.0: DeepSeek V4.1 Flash hits 28.5%, ahead of Gemini 4 Argon at 25.7%
SuSu_酥酥👅 @NFT_ChenOriginally posted 2026.10.28
Open original on X

🔥终于比较客观了!AA的 FrontierCode 2.0 出炉,DeepSeek V4.1 Flash 1017 直接 28.5%!真实工程能力开源第一! 对比一波:
🔹完胜 Kimi K3.1 Pro(25.5%)
🔹压过 Gemini 4 Argon(25.7%)
🔹高于 GPT-6 Luna(25.2%)
🔹小超 Wonder Muse(27.9%) 开源模型在“真能 merge 的工程判断力”上已经能打赢多款闭源中高端,性价比爆炸! 榜单远未饱和,中段差距最能看出实力。 此前 DeepSeek 被各家榜单严重低估了! #DeepSeek #FrontierCode #开源模型 #AI编程 #大模型 #Kimi #Gemini #GPT6 #梁文峰 #梁圣

This post quotes another post: x.com/nft_chen/status/2115282898861654160

x.com/nft_chen/status/2115310153444856187Archived 2026.10.29 10:06