gemini-4IMAGE
Gemini 4 被指只会刷榜、实际干活拉胯
爆料称 Gemini 4 在行业基准上表现亮眼,但员工真正拿它干活时效果明显变差,质疑又是 benchmaxxing。
Jimmy Apples 🍎/acc
@apples_jimmy28 天前收录原推发布于 2026.10.01

Jimmy Apples 🍎/acc @apples_jimmy原推发布于 2026.10.01
I swear if they are just benchmaxxing again “ while Gemini 4 has performed well on benchmarks the industry uses to gauge model efficacy, it does less well when employees actually put it to work “
这条是引用着另一条写的:x.com/googledeepmind/status/2105388084154056939
x.com/apples_jimmy/status/2105404503352840588采集于 2026.10.01 10:02