WHAT NEW IN X11.07 SAT

AI collections from X · 23 collections · 70,791 posts

gemini-4POST

Gemini 4 Argon is a repeat of Gemini 3 Pro, one user says

A user says Gemini 4 Argon scores very well on most benchmarks but performs poorly on reliability, hallucination and vibes-style evaluations.

Lisan al Gaib
@scaling01Archived 21 days agoOriginally posted 2026.10.16
Lisan al Gaib @scaling01Originally posted 2026.10.16
Open original on X

I feel like Gemini 4 Argon is a repeat of Gemini 3 Pro it scores extremely well on most benchmarks, but in the ones that measure reliability, hallucinations and vibes it sucks

This post quotes another post: “Gemini 4 Argon scores 165 on the Epoch Capabilities Index”

x.com/scaling01/status/2110818844730327332Archived 2026.10.16 10:09