WHAT NEW IN X11.07 SAT

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

gemini-4IMAGE

Argon still trails Opus 5.5 on a 3D task, comparison finds

Comparing Google's official Argon 3D demo with a version Opus 5.5 made in under a day, the author says Argon still lags clearly on realism and object placement.

Leon Lin
@LexnLinArchived 21 days agoOriginally posted 2026.10.16
Argon still trails Opus 5.5 on a 3D task, comparison finds (image 1 of 4)
Argon still trails Opus 5.5 on a 3D task, comparison finds (image 2 of 4)
Argon still trails Opus 5.5 on a 3D task, comparison finds (image 3 of 4)
Argon still trails Opus 5.5 on a 3D task, comparison finds (image 4 of 4)
Leon Lin @LexnLinOriginally posted 2026.10.16
Open original on X

Opus 5.5 is still WAY better than Argon at this 3d task. As you can see in the demo that Google shared, there are A LOT of things that either look very unrealistic, sloppy, or misplaced. They used some complex stuff, reference images, loops, multiple agents with visual critique, skills, etc. to create it, probably over many many hours, maybe even days. Whereas Opus made the one in the quoted video in less than a day, with a simple prompt + image references and it just nailed the realism better imo. You can clearly see that some things are placed incorrectly in the images here (from Google's demo), whereas in the Opus one, it knew exactly where things belong. And the trees looked more realistic, without leaves almost floating around, etc. So overall, Argon is a big improvement, but still a lot behind Opus 5.5 in 3D.

This post quotes another post: “Opus 5.5 builds a golden hour Japanese temple in Three.js”

x.com/lexnlin/status/2110851952934293849Archived 2026.10.16 10:11