VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation

• URL: http://arxiv.org/abs/2604.02580v1
• Date: Thu, 02 Apr 2026 23:33:58 GMT
• Title: VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
• Abstract summary: We introduce a platform VoxelCode, for analyzing code generation capabilities for 3D understanding and environment creation.<n>Our platform integrates natural language task specification, API-driven code execution in Unreal Engine, and a unified evaluation pipeline supporting both automated metrics and human assessment.
• Score: 15.578526245420859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating code generation models for 3D spatial reasoning requires executing generated code in realistic environments and assessing outputs beyond surface-level correctness. We introduce a platform VoxelCode, for analyzing code generation capabilities for 3D understanding and environment creation. Our platform integrates natural language task specification, API-driven code execution in Unreal Engine, and a unified evaluation pipeline supporting both automated metrics and human assessment. To demonstrate its utility, we construct VoxelCodeBench, a benchmark of voxel manipulation tasks spanning three reasoning dimensions: symbolic interpretation, geometric construction, and artistic composition. Evaluating leading code generation models, we find that producing executable code is far easier than producing spatially correct outputs, with geometric construction and multi-object composition proving particularly challenging. By open-sourcing our platform and benchmark, we provide the community with extensible infrastructure for developing new 3D code generation benchmarks and probing spatial reasoning in future models.

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)
• 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code [25.904997126319547]
  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.
  arXiv  Detail & Related papers  (2026-05-31T06:59:49Z)
• MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation [17.467056775887944]
  MUSE is a Text-to-CAD benchmark focused on complex, editable boundary representation assemblies.<n>MUSE evaluates generated models through a three-stage protocol: code check, geometric check, and design-intent alignment.<n> Experiments on closed-source and open-source LLMs reveal a clear failure cascade from executable code to valid geometry.
  arXiv  Detail & Related papers  (2026-05-27T15:01:59Z)
• Benchmarking PhD-Level Coding in 3D Geometric Computer Vision [43.42170296855238]
  We introduce GeoCodeBench, a benchmark that evaluates coding for 3D vision.<n>We evaluate eight representative open- and closed-source models to reflect the current ecosystem.<n>The best model, GPT-5, attains only 36.6% pass rate.
  arXiv  Detail & Related papers  (2026-03-31T17:50:55Z)
• Bioinspired123D: Generative 3D Modeling System for Bioinspired Structures [1.1458853556386797]
  We introduce Bioinspired123D, a lightweight and modular code-as-geometry pipeline that generates fabricable 3D structures directly through parametric programs.<n>At the core of Bioinspired123D is Bioinspired3D, a compact language model finetuned to translate natural language design cues into Blender Python scripts.<n>We evaluate performance on a new benchmark for 3D geometry script generation and show that Bioinspired123D demonstrates a near fourfold improvement over its non-finetuned base model.
  arXiv  Detail & Related papers  (2026-02-11T15:49:40Z)
• Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling [7.753074942497876]
  We introduce CodeProjectEval, a project-level code generation dataset built from 18 real-world repositories with 12.7 files and 2,388.6 lines of code per task.<n>We propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages.<n>Experiments show that ProjectGen achieves state-of-the-art performance, passing 52/124 test cases on the small-scale project-level code generation dataset DevBench.
  arXiv  Detail & Related papers  (2025-11-05T12:12:35Z)
• Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Models [0.0]
  This paper introduces a human in the loop framework for the quantitative evaluation of Large Language Models generated 3D models.<n>We propose a comprehensive suite of similarity and complexity metrics, including volumetric accuracy, surface alignment, dimensional fidelity, and topological intricacy.<n>Our findings demonstrate improved generation fidelity with increased semantic richness, with code level prompts achieving perfect reconstruction.
  arXiv  Detail & Related papers  (2025-09-06T11:04:15Z)
• Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework [12.995265721478132]
  We present a unified evaluation framework designed to assess the performance of 3D representations in reconstruction and generation.<n>We derive best practices over all steps involved in the 3D generation pipeline, including preprocessing, mesh reconstruction, compression with autoencoders, and generation.
  arXiv  Detail & Related papers  (2025-09-02T16:25:12Z)
• MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds [50.98900790623827]
  MeshCoder is a novel framework that reconstructs complex 3D objects from point clouds into editable Blender Python scripts.<n>We train a multimodal large language model (LLM) that translates 3D point cloud into executable Blender Python scripts.<n>Our approach achieves superior performance in shape-to-code reconstruction tasks and also facilitates intuitive geometric and topological editing.
  arXiv  Detail & Related papers  (2025-08-20T17:50:15Z)
• Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations [114.57192386025373]
  Object-X is a versatile multi-modal 3D representation framework.<n>It can encoding rich object embeddings and decoding them back into geometric and visual reconstructions.<n>It supports a range of downstream tasks, including scene alignment, single-image 3D object reconstruction, and localization.
  arXiv  Detail & Related papers  (2025-06-05T09:14:42Z)
• Agentic 3D Scene Generation with Spatially Contextualized VLMs [67.31920821192323]
  We introduce a new paradigm that enables vision-language models to generate, understand, and edit complex 3D environments.<n>We develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context.<n>Results show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work.
  arXiv  Detail & Related papers  (2025-05-26T15:28:17Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects [53.4874127399702]
  We propose a language agent with chain-of-3D-thoughts (L3GO), an inference-time approach that can reason about part-based 3D mesh generation. We develop a new benchmark, Unconventionally Feasible Objects (UFO), as well as SimpleBlenv, a wrapper environment built on top of Blender. Our approach surpasses the standard GPT-4 and other language agents for 3D mesh generation on ShapeNet.
  arXiv  Detail & Related papers  (2024-02-14T09:51:05Z)

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.