WHAT NEW IN X10.30 FRI

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

gemini-4THREAD

LuminaBench says its own testing puts Gemini 4 Pro at the frontier

LuminaBench links a paywalled Bloomberg report on Google employee skepticism toward the new Gemini model and says its own testing shows Gemini 4 Pro is a frontier model.

Lumina
@LuminaBenchArchived 28 days agoOriginally posted 2026.10.01
THREADPosted in 2 parts
  1. Source here, heads up it is paywalled, also my own personal take on Gemini 4 pro is that it's frontier from my own testing with it https://www.bloomberg.com/news/articles/2026-09-30/google-grapples-with-employee-skepticism-about-new-gemini-model?utm_source=chatgpt.com

  2. 🚨 Gemini 4 is reportedly getting pushback for benchmaxxing Bloomberg says some employees with direct access think it looks much better on benchmarks than it does in actual use, especially coding 💀 Google dispute this and say there’s “large consensus” internally that Gemini 4 is at the frontier

    LuminaBench says its own testing puts Gemini 4 Pro at the frontier (thread part 2)
Lumina @LuminaBenchOriginally posted 2026.10.01
Open original on X
x.com/luminabench/status/2105408123313999974Archived 2026.10.01 09:57