HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13 languages, written by native or highly proficient speakers. Questions are designed to be extremely challenging. Each question targets a concise, publicly verifiable answer whose discovery requires locating obscure evidence, following multi-step…

arxiv.org ·2d ago

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

More in AI

The Four Horsemen of Agentic Coding

Maryland Gov. Wes Moore Tees Up State Leaders’ AI Regulation Plan

AI campaign deepfakes are starting to draw legal threats

Vietnam’s AI Adoption Jumps to 26%, but Most Adopters Are Still Experimenting

Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection

The relationship between AI and influencers is … complicated