# WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

arXiv: https://arxiv.org/abs/2606.01869 · HTML: https://mlsanity.com/paper/2606.01869/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 30 of 31)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://mlsanity.com/paper/2402.05930/) (2024)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [PHYRE: A New Benchmark for Physical Reasoning](https://mlsanity.com/paper/1908.05656/) (2019)
- [Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset](https://mlsanity.com/paper/2403.09029/) (2024)
- [PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI](https://mlsanity.com/paper/2404.09465/) (2024)
- [pix2code: Generating Code from a Graphical User Interface Screenshot](https://mlsanity.com/paper/1705.07962/) (2017)
- [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://mlsanity.com/paper/2505.03733/) (2025)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping](https://mlsanity.com/paper/2411.03292/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation](https://mlsanity.com/paper/2507.04952/) (2025)
- [Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks](https://mlsanity.com/paper/2505.07473/) (2025)
- [Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review](https://mlsanity.com/paper/2510.00328/) (2025)
- [GameDevBench: Evaluating Agentic Capabilities Through Game Development](https://mlsanity.com/paper/2602.11103/) (2026)
- [Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances](https://mlsanity.com/paper/2409.11884/) (2024)
- [FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation](https://mlsanity.com/paper/2506.13832/) (2025)
- [WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics](https://mlsanity.com/paper/2601.02430/) (2026)
- [WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code](https://mlsanity.com/paper/2506.07818/) (2025)
- [Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation](https://mlsanity.com/paper/2508.02374/) (2025)
- [GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark](https://mlsanity.com/paper/2412.09997/) (2024)
- [IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?](https://mlsanity.com/paper/2509.24709/) (2025)
- [WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality](https://mlsanity.com/paper/2510.18560/) (2025)
- [V-GameGym: Visual Game Generation for Code Large Language Models](https://mlsanity.com/paper/2509.20136/) (2025)
- [DeepResearch-Slice: Bridging the Retrieval-Utilization Gap via Explicit Text Slicing](https://mlsanity.com/paper/2601.03261/) (2025)
- [Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation](https://mlsanity.com/paper/2602.11635/) (2026)

## Built on by (most cited first, 9 of 9)

- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective](https://mlsanity.com/paper/2608.30563/) (2026)
- [Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes](https://mlsanity.com/paper/2609.36777/) (2026)
- [LEGO-Anything: Coding Agents for 3D Scene Reconstruction](https://mlsanity.com/paper/2609.36380/) (2026)
- [Second-Order Problem Solving for Recursive Self-Improvement in Formal Verification](https://mlsanity.com/paper/2610.05701/) (2026)
- [WorldBench: Evaluating LLMs on Three.js Voxel World Generation](https://mlsanity.com/paper/2610.10622/) (2026)
- [MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting](https://mlsanity.com/paper/2610.10759/) (2026)
- [MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers](https://mlsanity.com/paper/2610.12624/) (2026)
- [ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling](https://mlsanity.com/paper/2610.15166/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language. Browser-native 3D, commonly built with Three.js, is a natural next frontier: generated programs must integrate assets, obey spatial and physical constraints, and keep user-facing controls synchronized with hidden runtime state. Existing web-generation benchmarks and evaluators, however, largely observe only pixels or DOM nodes, while the mechanics of a Three.js world unfold inside an opaque <canvas>. We introduce WorldCoder-Bench, a benchmark for autonomous, physically grounded 3D world synthesis. WorldCoder-Bench contains 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, with optional .glb assets and hidden behavioral contracts. We further propose StateProbe, an execution-based protocol that probes generated programs in a sandboxed browser and verifies hidden, mutation-hardened contracts over runtime states and transitions. Beyond verification coverage, we report Return on Automation and Time Efficiency Multiplier to measure correctness-adjusted cost and time savings. Across nine frontier models, the best system reaches only 27.8% verification coverage on WorldCoder-Core and 19.9% on WorldCoder-Robust, with failures dominated by state-schema drift and broken interaction chains rather than missing scene elements. Utility metrics further show that cheap or fast models can still provide substantial value on easier domains. WorldCoder-Bench is available at https://anonymous.4open.science/r/WorldCoder-Bench/.