# TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents

arXiv: https://arxiv.org/abs/2605.16909 · HTML: https://mlsanity.com/paper/2605.16909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 36 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents](https://mlsanity.com/paper/2408.06327/) (2024)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning](https://mlsanity.com/paper/2401.10727/) (2024)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [ToolTalk: Evaluating Tool-Usage in a Conversational Setting](https://mlsanity.com/paper/2311.10775/) (2023)
- [Less is More: Focus Attention for Efficient DETR](https://mlsanity.com/paper/2307.12612/) (2023)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection](https://mlsanity.com/paper/2506.00979/) (2025)
- [MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark](https://mlsanity.com/paper/2508.07575/) (2025)
- [OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents](https://mlsanity.com/paper/2510.24563/) (2025)
- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark](https://mlsanity.com/paper/2511.17729/) (2025)

## Abstract (arXiv)

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.