P3D-Bench - Text-to-3D Parametric Geometry: leaderboard

Metric: Geometry bucket score (0-100) (equal-weight mean of normalized F-scores at 0.05 and 0.01, normal consistency, Chamfer distance and IoU) on 400 Text-to-3D cases from parametric specifications (minimal JSON and OpenSCAD outputs), the model writes a parametric CAD program that is compiled, meshed and aligned to the ground truth; invalid outputs take the worst value; each general model runs with its maximum thinking budget; averaged over the output formats; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 9 models tracked.

Top models

#ModelScore
1GPT-5.5 (xHigh)70.6
2Gemini 3.1 Pro (Preview) (High)69.9
3Claude Opus 4.6 (Max)69.2
4Qwen 3.6 Plus (Thinking)65
5DeepSeek V4 Pro (Max)64.7
6Seed 2.0 Pro (High)63.3

Interactive version: theaggregate.ai/benchmark?slug=p3d-bench-text-to-3d-parametric-geometry · How It Works · Data refreshed daily, snapshot 2026-09-29.