Harness comparisonBenchmark: GLASS CATHEDRAL by @AlicanKiraz0AI Coding
GLASS CATHEDRAL fracture benchmark, four harnesses — Pi vs Droid vs OpenAI Codex vs OMP
GPT-6 Luna at high effort runs the GLASS CATHEDRAL fracture benchmark in Pi, OMP, Droid and Codex CLI: three Gothic stained-glass windows, 150–200 breakable glass fragments with XPBD constraints, in one HTML file.
Same model in every harness: GPT-6 Luna. More OpenAI Codex vs Pi. All harness comparisons.
The post, itemised
- Task
- GLASS CATHEDRAL fracture benchmark, four harnesses
- Category
- Simulations
- Mode
- Not stated
- Posted
- Video length
- 77.5 s
- Likes
- 40
- Views
- 1,772
- Bookmarks
- 8
- Sponsored
- No
NotesScores out of 10 from GPT-6 Astra Pro as judge LLM. Planning-first, then development, in every tool.
Cost & time, as stated in the postAs stated: Droid $0.17, 15 min; Pi $0.15, 42 min; Codex CLI $0.34, 24 min; OMP $0.83, 1 h 17 min.
Related
Posted by @AlicanKiraz0 on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
