WHAT NEW IN X10.30 FRI

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

gemini-4IMAGE

Gemini 4 benchmark scores diverge from real-world tasks, report says

Sources tell reporters there is a gap between Gemini 4's benchmark scores and its performance on real-world tasks, including some coding work, and internal opinions are mixed on whether it has caught up to OpenAI and Anthropic.

Davey Alba
@daveyalbaArchived 28 days agoOriginally posted 2026.10.01
Gemini 4 benchmark scores diverge from real-world tasks, report says
Davey Alba @daveyalbaOriginally posted 2026.10.01
Open original on X

NEW: As Google unveils Gemini 4, sources tell us there's a gap b/w how it scores on benchmarks and how it performs on real-world tasks, including certain coding work. Internally, opinions are mixed on whether it has caught up to OpenAI & Anthropic. Scoop w/@byJuliaLove @EdLudlow

x.com/daveyalba/status/2105398718178443512Archived 2026.10.01 10:02