Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark
A recent benchmark tested various AI coding tools on their ability to create a 3D model of the Pantheon using OpenSCAD. Google Antigravity 2.0 achieved the highest score for its detailed and accurate representation, while other models showed varying levels of success. The benchmark aimed to evaluate how well these tools could translate architectural references into parametric CAD code.
- ▪The benchmark involved six AI coding tools tasked with building the Pantheon model in OpenSCAD.
- ▪Google Antigravity 2.0 produced the strongest output, accurately incorporating real dimensions and architectural details.
- ▪ModelRift was recognized as the best non-autonomous result, utilizing an iterative annotation workflow.
Opening excerpt (first ~120 words) tap to expand
← Back to Blog May 21, 2026 OpenSCAD LLM Benchmark: Building the Pantheon A practical OpenSCAD LLM benchmark comparing Codex 5.5 High, Claude Sonnet, Claude Opus, Cursor Composer, Google Antigravity, and ModelRift on a detailed Pantheon model. openscadllmbenchmarkcad On this page Why Pantheon? Prompt Reference Images Results Workflow Notes Google Antigravity 2.0 / Gemini 3.5 Flash High ModelRift / Gemini Flash 3.0 Codex 5.5 High Claude Sonnet Cursor Composer Claude Opus Takeaways We ran a small practical benchmark: give several AI coding tools the same kind of task and ask them to build the Pantheon in OpenSCAD. ModelRift generates OpenSCAD for every 3D model on the platform.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at ModelRift — OpenSCAD code editor & AI 3D model builder.
Discussion
0 comments
