Harness comparisonAI Coding
3D Orbital Garden, three models ranked — OMP (Qwen 3.8 Flash Next) vs OMP (DeepSeek V4.1 Flash 1017) vs Claude Code (Claude Opus 5.5)
Scoreboard3
- Qwen 3.8 Flash NextAlibaba (Qwen)OMP
- Ranked third
- DeepSeek V4.1 Flash 1017DeepSeekOMP
- Ranked second
- Claude Opus 5.5AnthropicClaude CodeAuthor’s pick
- Ranked first
Prompt
3D Orbital Garden, three models rankedThe post doesn’t quote the prompt wording.
Opus 5.5 ranks first, DeepSeek V4.1 Flash 1017 second (the best 3D reasoning the author has seen from an open model), Qwen third.
@ZenMagnets’s view (paraphrased)
Qwen 3.8 Flash Next and DeepSeek V4.1 Flash 1017 (both in OMP) and Claude Opus 5.5 (in Claude Code) build the same 3D Orbital Garden. Opus and DeepSeek both named their app “Aurelia”.
Each side pairs a coding harness with its own model, so harness and model differences are mixed. All harness comparisons.
The post, itemised
- Task
- 3D Orbital Garden, three models ranked
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 30 s
- Likes
- 1
- Views
- 63
- Bookmarks
- 0
- Sponsored
- No
NotesThe full prompt and a GLM 5.3 Flash run are in the quoted @loktar00 post.
Related
Posted by @ZenMagnets on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
