3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code

• URL: http://arxiv.org/abs/2606.01057v1
• Date: Sun, 31 May 2026 06:59:49 GMT
• Title: 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
• Abstract summary: 3DCodeBench is a systematic benchmark for evaluating vision-language model (VLM) agents for procedural 3D generation in 3D modeling software.<n>We build 3DCodeArena, a ranking platform based on pairwise human preferences over generated 3D outputs.
• Score: 25.904997126319547
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently lack. Authoring such procedural content, however, demands deep expertise in 3D software APIs, parametric design, and code-level geometric reasoning. In this paper, we propose 3DCodeBench, a systematic benchmark for evaluating vision-language model (VLM) agents for procedural 3D generation in 3D modeling software. Specifically, 3DCodeBench evaluates how effectively 12 advanced VLMs can serve as procedural 3D modelers by translating text and image references into procedural code for 3D modeling software. Recognizing that automated metrics may not fully capture the perceptual quality of 3D shapes, we build 3DCodeArena, a ranking platform based on pairwise human preferences over generated 3D outputs. From extensive evaluations and results, we observe that: (1) Failures mostly arise from API mismatches, while successful renders still suffer from disconnected or floating 3D geometric components. (2) Test-time scaling, such as higher thinking budgets and multi-turn refinement, improves performance overall. Our findings highlight a critical need for high-quality procedural coding data to advance commercial VLMs. Furthermore, effective procedural 3D modeling requires a robust execution environment that provides high-fidelity feedback for iterative refinement. We release 3DCodeBench, including the curated large-scale dataset of multimodal (text/image) prompts, procedural code, 3D object triplets, evaluation protocol, and the public 3DCodeArena platform as a foundational toolkit for exploring VLM-based procedural 3D modelers.

Related papers

• 3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis [69.23609431485401]
  We propose and systematically evaluate a new 3D reconstruction paradigm, where 3D assets are constructed as executable code.<n>Our study shows that code as a 3D representation offers strong controllability and locality, yielding stronger edit fidelity and better preservation of unedited regions.
  arXiv  Detail & Related papers  (2026-06-09T06:46:29Z)
• DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation [16.60840648468348]
  We introduce DB-3DME, the dataset and benchmark for 3D mesh evaluation.<n>DB-3DME contains 2,619 synthetic 3D meshes paired with human ratings on Geometry and Prompt Adherence.<n>We fine-tune an open-weight VLM, Qwen-2.5-VL-7B, for 3D mesh evaluation by adapting the visual encoder while freezing the language model.
  arXiv  Detail & Related papers  (2026-06-08T20:17:49Z)
• Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity [78.7107376451476]
  Hi3DEval is a hierarchical evaluation framework tailored for 3D generative content.<n>We extend texture evaluation beyond aesthetic appearance by explicitly assessing material realism.<n>We propose a 3D-aware automated scoring system based on hybrid 3D representations.
  arXiv  Detail & Related papers  (2025-08-07T17:50:13Z)
• Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation [134.53804996949287]
  We introduce Eval3D, a fine-grained, interpretable evaluation tool that can faithfully evaluate the quality of generated 3D assets.<n>Our key observation is that many desired properties of 3D generation, such as semantic and geometric consistency, can be effectively captured.<n>Compared to prior work, Eval3D provides pixel-wise measurement, enables accurate 3D spatial feedback, and aligns more closely with human judgments.
  arXiv  Detail & Related papers  (2025-04-25T17:22:05Z)
• TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction [137.34863114016483]
  TAR3D is a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT)<n>We show that TAR3D can achieve superior generation quality over existing methods in text-to-3D and image-to-3D tasks.
  arXiv  Detail & Related papers  (2024-12-22T08:28:20Z)
• Learning 3D Representations from Procedural 3D Programs [6.915871213703219]
  We propose learning 3D representations from procedural 3D programs that automatically generate 3D shapes using simple primitives and augmentations.<n>Remarkably, the 3D representations learned from the procedurally generated 3D shapes perform on par with state-of-the-art representations learned from semantically recognizable 3D models.
  arXiv  Detail & Related papers  (2024-11-25T18:59:57Z)
• ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance [76.7746870349809]
  We present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling.
  arXiv  Detail & Related papers  (2024-03-19T03:39:43Z)
• 3D-GPT: Procedural 3D Modeling with Large Language Models [47.72968643115063]
  We introduce 3D-GPT, a framework utilizing large language models(LLMs) for instruction-driven 3D modeling. 3D-GPT positions LLMs as proficient problem solvers, dissecting the procedural 3D modeling tasks into accessible segments and appointing the apt agent for each task. Our empirical investigations confirm that 3D-GPT not only interprets and executes instructions, delivering reliable results but also collaborates effectively with human designers.
  arXiv  Detail & Related papers  (2023-10-19T17:41:48Z)
• GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images [72.15855070133425]
  We introduce GET3D, a Generative model that directly generates Explicit Textured 3D meshes with complex topology, rich geometric details, and high-fidelity textures. GET3D is able to generate high-quality 3D textured meshes, ranging from cars, chairs, animals, motorbikes and human characters to buildings.
  arXiv  Detail & Related papers  (2022-09-22T17:16:19Z)
• A Convolutional Architecture for 3D Model Embedding [1.3858051019755282]
  We propose a deep learning architecture to handle 3D models as an input. We show that the embedding representation conveys semantic information that helps to deal with the similarity assessment of 3D objects.
  arXiv  Detail & Related papers  (2021-03-05T15:46:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.