# OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies

arXiv: https://arxiv.org/abs/2608.22637 · HTML: https://mlsanity.com/paper/2608.22637/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 53 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 8 of 8)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation](https://mlsanity.com/paper/2505.14646/) (2025)
- [IKEA-Manual: Seeing Shape Assembly Step by Step](https://mlsanity.com/paper/2302.01881/) (2023)
- [CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation](https://mlsanity.com/paper/2512.23333/) (2025)
- [Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models](https://mlsanity.com/paper/2502.10090/) (2025)
- [SPAFormer: Sequential 3D Part Assembly with Transformers](https://mlsanity.com/paper/2403.05874/) (2024)
- [Mates2Motion: Learning How Mechanical CAD Assemblies Work](https://mlsanity.com/paper/2208.01779/) (2022)
- [AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects](https://mlsanity.com/paper/2605.12845/) (2026)

## Built on by (most cited first, 1 of 1)

- [NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction](https://mlsanity.com/paper/2609.20323/) (2026)

## Abstract (arXiv)

Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We introduce OmniCAD, a large-scale benchmark for assembly-aware 3D spatial reasoning across diverse industrial systems, including robotic mechanisms, automotive components, aerospace structures, and agricultural machinery. OmniCAD contains 25k mechanical assemblies, with an average of 12 parts per assembly and 21 types of mate relationships. Each assembly includes a human-verified ground-truth 3D model and renderings from 20 viewpoints. The benchmark evaluates three capabilities: (1) component-level 3D spatial reasoning, requiring prediction of part positions and orientations; (2) part-to-part relational reasoning, requiring identification of mating relationships and assembly constraints; and (3) tool-augmented agentic reasoning, where models iteratively select viewpoints, inspect visual evidence, and refine predictions. Experiments show that current VLMs struggle with industrial assembly reasoning, often producing inaccurate poses, invalid mating relationships, part interpenetration, and degraded performance as assembly complexity increases. We will open-source the benchmark, evaluation code, and tool interfaces to support research on accurate, physically valid, and scalable 3D assembly reasoning.