WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
This work addresses the need for improved multimodal and cross-lingual reasoning in web development automation, though it is incremental as it builds on prior benchmarks by unifying tasks.
The authors tackled the problem of evaluating multimodal multilingual website understanding and code generation by introducing WebMMU, a benchmark that unifies three core web tasks, and found that current multimodal large language models struggle with reasoning, grounding, and functional code editing, with performance gaps in tasks like mockup-to-code generation.
We present WebMMU, a multilingual benchmark that evaluates three core web tasks: (1) website visual question answering, (2) code editing involving HTML/CSS/JavaScript, and (3) mockup-to-code generation. Unlike prior benchmarks that treat these tasks separately, WebMMU unifies them using expert-annotated, real-world web data to assess models' abilities in complex multi-step reasoning, precise element grounding, and functional UI comprehension and coding. Our evaluation shows that while multimodal large language models (MLLMs) perform well on basic information extraction, they struggle with reasoning and grounding, editing code to preserve functionality, and generating design-to-code that maintains hierarchy and supports multilingual content. These findings reveal key limitations in current MLLMs and underscore the need for improved multimodal and cross-lingual reasoning to build future web agents capable of automating diverse web development tasks.