VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?

Junpeng Liu, Yifan Song, Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li, Xiang Yue

Research Area: Evaluation, LMs on diverse modalities and novel applications

Keywords: multimodal large language model, evaluation, web understanding, grounding

TL;DR: VisualWebBench: How Far Have LMMs Evolved in Web Page Understanding and Grounding?

Abstract: Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed for general multimodal tasks, failing to capture the unique characteristics of web pages, or focus on end-to-end web agent tasks, unable to measure fine-grained abilities such as OCR, understanding, and grounding. In this paper, we introduce VisualWebBench, a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks. VisualWebBench consists of seven tasks, and comprises 1.5K human-curated instances from 139 real websites, covering 87 sub-domains. We evaluate 16 open-source MLLMs, Gemini Pro, Claude-3 series, and GPT-4V(ision) on VisualWebBench, revealing significant challenges and performance gaps. Further analysis highlights the limitations of current MLLMs, including inadequate grounding in text-rich environments and subpar performance with low-resolution image inputs. We believe VisualWebBench will serve as a valuable resource for the research community and contribute to the creation of more powerful and versatile MLLMs for web-related applications.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 145