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

arXiv:2610.03574v1 Announce Type: new Abstract: 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 clue chains, or inspecting heterogeneous sources such as videos, scanned documents, images, or maps. Easier questions are filtered out by evaluating them with models without internet access to reduce the likelihood that they can be answered with parametric knowledge alone. We evaluate several models using provider-native search and a shared external retrieval harness under a common agent protocol. To contextualize model performance and effort, we also conduct a human evaluation on a sample of the questions. HyperBrowseComp provides a challenging testbed for persistent information seeking across languages and evidence modalities, with difficulty arising from discovering and connecting evidence on the open web.

Related

• MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
• WorldBench: Culturally Grounded Benchmark for Multilingual Agents
• TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents

Source: arXiv cs.AI | 2026-10-05