# MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

arXiv: https://arxiv.org/abs/2605.28579 · HTML: https://mlsanity.com/paper/2605.28579/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 27 of 27)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [TripoSR: Fast 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/2403.02151/) (2024)
- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [LLaVA-Critic: Learning to Evaluate Multimodal Models](https://mlsanity.com/paper/2410.02712/) (2024)
- [Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation](https://mlsanity.com/paper/2401.06591/) (2024)
- [CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM](https://mlsanity.com/paper/2411.04954/) (2024)
- [Generating CAD Code with Vision-Language Models for 3D Designs](https://mlsanity.com/paper/2410.05340/) (2024)
- [CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs](https://mlsanity.com/paper/2412.19663/) (2024)
- [Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models](https://mlsanity.com/paper/2501.19054/) (2025)
- [MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria](https://mlsanity.com/paper/2311.13951/) (2023)
- [Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts](https://mlsanity.com/paper/2409.17106/) (2024)
- [Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following](https://mlsanity.com/paper/2511.21662/) (2025)
- [CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation](https://mlsanity.com/paper/2603.26512/) (2026)
- [Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection](https://mlsanity.com/paper/2603.04337/) (2026)
- [Text2CAD: Text to 3D CAD Generation via Technical Drawings](https://mlsanity.com/paper/2411.06206/) (2024)
- [Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?](https://mlsanity.com/paper/2505.08468/) (2025)
- [Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models](https://mlsanity.com/paper/2505.19490/) (2025)
- [Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis](https://mlsanity.com/paper/2602.13028/) (2026)
- [ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation](https://mlsanity.com/paper/2604.10992/) (2026)
- [EvoCAD: Evolutionary CAD Code Generation with Vision Language Models](https://mlsanity.com/paper/2510.11631/) (2025)
- [GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?](https://mlsanity.com/paper/2602.06013/) (2026)
- [K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge](https://mlsanity.com/paper/2602.09411/) (2026)
- [A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation](https://mlsanity.com/paper/2506.09427/) (2025)
- [Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation](https://mlsanity.com/paper/2603.00546/) (2026)

## Built on by (most cited first, 8 of 8)

- [P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning](https://mlsanity.com/paper/2606.11152/) (2026)
- [CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulation](https://mlsanity.com/paper/2608.09296/) (2026)
- [CADENA: Stepwise CAD Reverse Engineering](https://mlsanity.com/paper/2608.00799/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026)
- [CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design](https://mlsanity.com/paper/2609.16251/) (2026)
- [Test-Time Scaling for CAD Generation via Verifier-Free Consensus Selection](https://mlsanity.com/paper/2608.09706/) (2026)
- [RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents](https://mlsanity.com/paper/2609.03773/) (2026)
- [A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?](https://mlsanity.com/paper/2609.39564/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus primarily on generating single-part CAD models and evaluate them using geometric similarity metrics that fail to capture functionality, manufacturability, and assemblability. To address this gap, we introduce MUSE, a Text-to-CAD benchmark focused on complex, editable boundary representation (B-Rep) assemblies. MUSE pairs practical design instances with structured Design Specifications and evaluates generated models through a three-stage protocol: code check, geometric check, and design-intent alignment. The final stage uses design-specific rubrics to assess functionality, manufacturability, and assemblability, moving beyond shape matching toward practical design quality. To enable scalable evaluation, we use a rubric-based visual language model (VLM) judge and validate its reliability through human annotation. Experiments on closed-source and open-source LLMs reveal a clear failure cascade from executable code to valid geometry and finally to engineering-ready design, with even the strongest models achieving limited success on fine-grained engineering criteria. Together, MUSE provides a realistic benchmark and evaluation framework for advancing Text-to-CAD from geometric generation toward true engineering design. Our project website, including the leaderboard, dataset, and code, is available at https://dong7313.github.io/muse-benchmark/.