gemini-4IMAGE

Gemini 4 scores well on benchmarks but underperforms in real work, report says

A report says Gemini 4 performs well on industry benchmarks but does less well when employees actually use it for work, raising benchmaxxing concerns.

Jimmy Apples 🍎/acc

@apples_jimmyArchived 28 days agoOriginally posted 2026.10.01

Gemini 4 scores well on benchmarks but underperforms in real work, report says

Jimmy Apples 🍎/acc @apples_jimmyOriginally posted 2026.10.01

Open original on X

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 “

This post quotes another post: x.com/googledeepmind/status/2105388084154056939

x.com/apples_jimmy/status/2105404503352840588Archived 2026.10.01 10:02