mlsanityData to 7 Oct 2026

Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification

arXiv 2603.26648 ↗First posted 27 Mar 2026cs.SE cs.AIcited by 16

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 22 of its 35 references that are in the map. First posted on arXiv 27 Mar 2026.

Builds on

22 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models25 Jan

Other references · 21

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2024A Survey on LLM-as-a-Judgecited by 1,384
  8. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  9. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  10. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  11. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
  12. 2024Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineeringcited by 146
9 more
  1. 2024Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Datasetcited by 126
  2. 2023Self-planning Code Generation with Large Language Modelscited by 121
  3. 2025A Survey on Code Generation with LLM-based Agentscited by 104
  4. 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratchcited by 66
  5. 2023CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulescited by 58
  6. 2026Seed1.8 Model Card: Towards Generalized Real-World Agencycited by 47
  7. 2024WebCode2M: A Real-World Dataset for Code Generation from Webpage Designscited by 43
  8. 2023ToolCoder: Teach Code Generation Models to use API search toolscited by 37
  9. 2026WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubricscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agentscited by 30
  2. 2026The Verification Horizon: No Silver Bullet for Coding Agent Rewardscited by 6
  3. 2026HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTMLcited by 2
  4. 2026Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generationcited by 2
  5. 2026Qwen3.8-Omni: Towards Native Omni-Modal Agentscited by 2
  6. 2026JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agentscited by 1
  7. 2026OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectoriescited by 1
  8. 2026VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generationcited by 1
  9. 2026RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agentscited by 1
  10. 2026Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliabilitycited by 0
  11. 2026UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generationcited by 0
  12. 2026MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modificationcited by 0
4 more
  1. 2026Agentic Visual Generation: From Generative Models to Agentic Controlcited by 0
  2. 2026ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Taskscited by 0
  3. 2026GameASG-Bench: Benchmarking Autonomous Software Generation for Game Developmentcited by 0
  4. 2026AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
  2. 2026LongWebBench: Evaluating Structural and Functional Webpage Generation in Long-Horizon Settings
  3. 2026CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception
  4. 2025WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
  5. 2026InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?
  6. 2026Framework and Benchmark for Code-Driven Agentic Testing in Web Development
  7. 2026VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
  8. 2024Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping