WHAT NEW IN X10.30 FRI

AI collections from X · 22 collections · 61,986 posts

Back to No.008 Gemini 4 Pro / Flash: benchmarks, hands-on tests and leaksUpdated 11 hours ago
gemini-4THREAD

LuminaBench compares four models on the same voxel pagoda prompt

The same voxel pagoda prompt run through Sonnet 5.5, Gemini 4 Pro, GPT-6 Sol and Luna shows clear style differences, with Gemini 4 Pro using checkpoint 2 from its Arena run a few days earlier.

Lumina
@LuminaBenchArchived 2026.09.29Originally posted 2026.09.28
THREADPosted in 2 parts

  1. 🚨 Sonnet 5.5 vs Gemini 4 Pro vs GPT 6 Sol & Luna Same voxel pagoda prompt across all 4 OpenAI models seem to have a drastically different style though, also Gemini 4 pro is from checkpoint 2 when it was in arena a couple days ago

    This post quotes another post: x.com/luminabench/status/2104565586114056532

  2. @promptacisi Gemini 4 Pro is the fastest by far too

Lumina @LuminaBenchOriginally posted 2026.09.28
Open original on X
x.com/luminabench/status/2104598576160456967Archived 2026.09.29 09:56
Open original on X