BrowseComp-VL

multimodal

Multilingual: no

BrowseComp-VL is the vision-language variant of BrowseComp, evaluating multimodal models on web browsing comprehension tasks that require processing visual web page content alongside text.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 1. Categories: agents, multimodal, search, vision. Language: en. Verified by llm-stats: no.