P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning

Hugging Face Daily Papers Papers

Summary

This paper introduces P3D-Bench, a benchmark for evaluating multimodal large language models on parametric 3D generation tasks, including text-to-3D, image-to-3D, and assembly-3D, with metrics for geometric precision, semantic alignment, and part-level structure.

Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for 3D generation powered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate a parametric 3D program that is geometrically precise, semantically aligned and assembly-consistent. We introduce P3D-Bench, a benchmark for parametric 3D generation. Unlike a 3D mesh, a parametric 3D program exposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design's structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D, Image-to-3D and Assembly-3D) and scores each output for executability, geometric fidelity, topology, text-grounded constraints, multiview semantic alignment and part-level structure. We evaluate frontier MLLMs and text-only LLMs on 400 text cases, 400 image cases and 203 annotated assemblies, with domain-specific models as reference points. Our extensive evaluation yields three findings. First, assemblies are the hardest setting, where models still fail to compose multiple parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry and part-level structure in parametric 3D generation.
Original Article
View Cached Full Text

Cached at: 06/15/26, 09:02 AM

Paper page - P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning

Source: https://huggingface.co/papers/2606.11152 Published on Jun 9

·

Submitted byhttps://huggingface.co/yangyk

杨忆康on Jun 15

Abstract

Parametric 3D generation benchmark evaluates models on geometric precision, semantic alignment, and assembly consistency through code-based modeling tasks.

Multimodal large language modelscan write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for3D generationpowered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate aparametric 3D programthat is geometrically precise, semantically aligned andassembly-consistent. We introduce P3D-Bench, a benchmark for parametric3D generation. Unlike a 3D mesh, aparametric 3D programexposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design’s structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D,Image-to-3DandAssembly-3D) and scores each output forexecutability,geometric fidelity,topology, text-grounded constraints,multiview semantic alignmentandpart-level structure. We evaluate frontier MLLMs and text-only LLMs on 400 text cases, 400 image cases and 203 annotated assemblies, with domain-specific models as reference points. Our extensive evaluation yields three findings. First, assemblies are the hardest setting, where models still fail to compose multiple parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry andpart-level structurein parametric3D generation.

View arXiv pageView PDFProject pageGitHub37Add to collection

Get this paper in your agent:

hf papers read 2606\.11152

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.11152 in a model README.md to link it from this page.

Datasets citing this paper1

#### SpatiaOS/P3D-Bench Viewer• Updated3 days ago • 1.4k • 156

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.11152 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use

arXiv cs.CL

This paper introduces PhysTool-Bench, a benchmark for evaluating multimodal large language models' ability to recognize and plan the use of physical tools in real-world scenes. The authors find that even the best model identifies only 58.7% of tools and completes just 21.0% of queries end-to-end, revealing a two-level deficit in perception and functional commonsense.