WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,925 posts

New todaydeepseek-v4.1IMAGE

Intelligence Index 5.0: DeepSeek V4.1 Flash scores 32, 26 behind Opus 5.5

The ranking post puts Opus 5.5 at 58, GPT-6 Astra at 57 and GPT-6.1 Sol at 55, with DeepSeek V4.1 Flash and GLM-5.3 tied at 32, and adds a coding test judged by real repo maintainers.

Ethan@liuyejinghong
@MartinM91217805Archived 9 hours agoOriginally posted 2026.10.28
Intelligence Index 5.0: DeepSeek V4.1 Flash scores 32, 26 behind Opus 5.5
Ethan@liuyejinghong @MartinM91217805Originally posted 2026.10.28
Open original on X

🚨 AI 智力榜单 5.0 大洗牌!最炸裂的不是谁登顶,而是开源差距越拉越大了? 🥇 Claude Opus 5.5:58 🥈 GPT-6 Astra:57 🥉 GPT-6.1 Sol:55 DeepSeek V4.1 Flash、GLM-5.3(已发布权重)仅 32 分,落后榜首整整 26 分! 更狠的是新编码测试:让真实仓库维护者评判 AI 的代码值不值得合并。 会刷榜 ≠ 能交付。 问题来了:你敢让 AI 的 PR 直接进主分支吗?

x.com/martinm91217805/status/2115271248427270372Archived 2026.10.28 12:04