# VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation arXiv: https://arxiv.org/abs/2604.02580 ยท HTML: https://mlsanity.com/paper/2604.02580/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Video-generation world models and simulators, one of 11 directions in World models. - Builds on 29 of its 41 references that are in the map. - First posted on arXiv 2 Apr 2026. ## Placed in - World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/) - LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/) ## Builds on (most cited first, 29 of 29) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021) - [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022) - [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022) - [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023) - [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022) - [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019) - [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021) - [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023) - [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019) - [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023) - [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022) - [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023) - [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016) - [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022) - [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022) - [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016) - [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023) - [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023) - [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023) - [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022) - [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024) - [SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning](https://mlsanity.com/paper/2104.05832/) (2021) - [3D generation on ImageNet](https://mlsanity.com/paper/2303.01416/) (2023) - [BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement](https://mlsanity.com/paper/2412.14203/) (2024) - [MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds](https://mlsanity.com/paper/2508.14879/) (2025) - [PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer](https://mlsanity.com/paper/2505.04622/) (2025) ## Built on by (most cited first, 8 of 8) - [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://mlsanity.com/paper/2606.01057/) (2026) - [Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning](https://mlsanity.com/paper/2608.27549/) (2026) - [P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning](https://mlsanity.com/paper/2606.11152/) (2026) - [SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation](https://mlsanity.com/paper/2607.01766/) (2026) - [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026) - [Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning](https://mlsanity.com/paper/2606.07602/) (2026) - [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026) - [PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction](https://mlsanity.com/paper/2610.17288/) (2026) ## Abstract (arXiv) 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.