# PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

arXiv: https://arxiv.org/abs/2510.09507 · HTML: https://mlsanity.com/paper/2510.09507/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 40 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control](https://mlsanity.com/paper/2502.05855/) (2025)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [Magma: A Foundation Model for Multimodal AI Agents](https://mlsanity.com/paper/2502.13130/) (2025)
- [Ovis2.5 Technical Report](https://mlsanity.com/paper/2508.11737/) (2025)
- [DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding](https://mlsanity.com/paper/2411.14347/) (2024)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios](https://mlsanity.com/paper/2401.17167/) (2024)
- [ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://mlsanity.com/paper/2501.02506/) (2025)
- [Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation](https://mlsanity.com/paper/2508.13998/) (2025)

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

- [TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models](https://mlsanity.com/paper/2511.13704/) (2025)
- [A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning](https://mlsanity.com/paper/2512.14442/) (2025)
- [OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization](https://mlsanity.com/paper/2602.07064/) (2026)
- [Panoramic Affordance Prediction](https://mlsanity.com/paper/2603.15558/) (2026)
- [NewtPhys: Do Foundation Models Understand Newtonian Physics?](https://mlsanity.com/paper/2606.03986/) (2026)
- [CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding](https://mlsanity.com/paper/2608.30289/) (2026)
- [ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?](https://mlsanity.com/paper/2606.07962/) (2026)
- [EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos](https://mlsanity.com/paper/2609.39378/) (2026)
- [HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution](https://mlsanity.com/paper/2610.02089/) (2026)

## Abstract (arXiv)

The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysToolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. It assesses capabilities across three distinct difficulty levels: (1) Tool Recognition: Requiring the recognition of a tool's primary function. (2) Tool Understanding: Testing the ability to grasp the underlying principles of a tool's operation. (3) Tool Creation: Challenging the model to fashion a new tool from surrounding objects when conventional options are unavailable. Our comprehensive evaluation of 32 MLLMs-spanning proprietary, open-source, specialized embodied, and backbones in VLAs-reveals a significant deficiency in tool understanding. Furthermore, we provide an in-depth analysis and propose preliminary solutions. Code and dataset are publicly available.