P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning
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.
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
M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
This paper introduces M3R-Bench, a unified evidence-grounded benchmark for multimodal metaphor understanding with 1,000 image-text instances, and proposes M3R-Reasoner, an 8B-parameter model combining curriculum-based reasoning supervision and reinforcement learning that outperforms larger proprietary models.
BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs
BilliardPhys-Bench is a new benchmark that tests multimodal LLMs on physical reasoning using synthetic billiards scenarios, requiring predictions of collisions and final ball positions. The paper finds that current models struggle with longer simulations and exhibit a 'stasis bias' of predicting no interaction when uncertain.
PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design
PolyBridgeBench is a new executable benchmark for evaluating multimodal LLMs on physics-grounded bridge design tasks, revealing gaps between deterministic validity and dynamic success in structure synthesis and repair.
3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
This paper introduces 3DCodeBench, a benchmark for evaluating vision-language models on procedural 3D modeling via code, and 3DCodeArena, a ranking platform based on pairwise human preferences.
Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use
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.