Harness comparisonAI Coding
Night Tokyo Halloween alley with yokai — Claude Code (Claude Opus 5.5) vs OpenAI Codex (GPT-6.1 Sol) vs Google Antigravity (Gemini 4 Argon)
Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Argon get the same prompt, one shot each: a night Tokyo alley where a paper lantern and a one-legged umbrella yokai come out when you click.
Each side pairs a coding harness with its own model, so harness and model differences are mixed. More Claude Code vs OpenAI Codex. More Google Antigravity vs OpenAI Codex. More Google Antigravity vs Claude Code. All harness comparisons.
The post, itemised
- Task
- Night Tokyo Halloween alley with yokai
- Category
- 3D & Shaders
- Mode
- One shot
- Posted
- Video length
- 19.5 s
- Likes
- 2
- Views
- 74
- Bookmarks
- 0
- Sponsored
- No
Cost & time, as stated in the postAs stated: Claude Opus 5.5 $15.23, 72 min; GPT-6.1 Sol $0.29, 6 min; Gemini 4 Argon $2.42, 48 min (the poster says Argon’s time includes “Model unavailable, retrying” errors).
Related
Posted by @sprinntt on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
