AI Coding
Mario World 1-1 drawn in code, 4 agents — Claude Opus 5.5 vs GPT-6.1 Sol vs Muse Wonder 1.0 vs Gemini 4 Argon
Claude Opus 5.5, GPT-6.1 Sol, Muse Wonder and Gemini 4 Argon get one prompt: recreate Mario World 1-1 with no assets, drawing everything in code.
The post, itemised
- Kind
- Side-by-side
- Task
- Mario World 1-1 drawn in code, 4 agents
- Category
- Games
- Mode
- Not stated
- Posted
- Video length
- 12 s
- Likes
- 0
- Views
- 3
- Bookmarks
- 0
- Sponsored
- No
NotesThe author notes Opus used 15x the tokens of Sol and asks if it was worth it.
Cost & time, as stated in the postAs stated: Opus 5.5 15 min, 1.5M tokens; GPT-6.1 Sol 4.5 min, 99K tokens; Muse Wonder 4 min, 171K tokens; Gemini 4 Argon did not finish.
Related
Posted by @maker_evan on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
