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

Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:41393-41415, 2026.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-he26n, title = {{V}ision2{W}eb: A Hierarchical Benchmark for Visual Website Development with Agent Verification}, author = {He, Zehai and Hong, Wenyi and Yang, Zhen and Pan, Ziyang and Liu, Mingdao and Gu, Xiaotao and Tang, Jie}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {41393--41415}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/he26n/he26n.pdf}, url = {https://proceedings.mlr.press/v306/he26n.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification %A Zehai He %A Wenyi Hong %A Zhen Yang %A Ziyang Pan %A Mingdao Liu %A Xiaotao Gu %A Jie Tang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-he26n %I PMLR %P 41393--41415 %U https://proceedings.mlr.press/v306/he26n.html %V 306 %X 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.
APA
He, Z., Hong, W., Yang, Z., Pan, Z., Liu, M., Gu, X. & Tang, J.. (2026). Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:41393-41415 Available from https://proceedings.mlr.press/v306/he26n.html.

Related Material