Yutori

Last updated Aug 05, 2026

Online-Mind2Web Leaderboard

The official leaderboard's latest evaluation data, as reported by our Scout

Markdown for agents

Human evaluation table selected

AgentModelOrganizationSourceEasyMediumHardAverage SRDate
HarkHark HandoffHarkCareerflow.ai100.095.0100.097.7%Aug 04, 2026
Navigatorn1.5-latestYutoriCareerflow.ai100.096.596.197.3%Jun 28, 2026
ACT-2GPT-5.4EnhansCareerflow.ai93.094.389.992.7%Aug 04, 2026
Navigatorn1-preview-11-2025YutoriHalluminate90.176.271.178.7%Nov 18, 2025
Google Computer Use (09-2025)Gemini 2.5 Computer UseGoogle DeepMindGoogle DeepMind77.171.355.469.0%Sep 29, 2025
OperatorOpenAI Computer-Using AgentOpenAIOSU NLP83.158.043.261.3%Mar 22, 2025
ACT-1-20250814o3-2025-04-16 and Claude-sonnet-4-20250514EnhansEnhans81.954.535.157.3%Aug 23, 2025
Claude Computer Use 3.7 (w/o thinking)Claude-3-7-sonnet-20250219AnthropicOSU NLP90.449.032.456.3%Apr 20, 2025
ACT-1-20250703o3-2025-04-16 and Claude-sonnet-4-20250514EnhansEnhans65.146.223.045.7%Jul 16, 2025
SeeActgpt-4o-2024-08-06OSUOSU NLP60.225.28.130.7%Mar 22, 2025
Browser Usegpt-4o-2024-08-06Browser UseOSU NLP55.426.68.130.0%Mar 22, 2025
Claude Computer Use 3.5claude-3-5-sonnet-20241022AnthropicOSU NLP56.620.314.929.0%Mar 22, 2025
Agent-Egpt-4o-2024-08-06Emergence AIOSU NLP49.426.66.828.0%Mar 22, 2025

Frequently asked questions

Resources

Citation
@article{xue2025illusionprogressassessingcurrent,
  title={An Illusion of Progress? Assessing the Current State of Web Agents},
  author={Tianci Xue and Weijian Qi and Tianneng Shi and Chan Hee Song and
          Boyu Gou and Dawn Song and Huan Sun and Yu Su},
  year={2025},
  eprint={2504.01382},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2504.01382},
}