Blog post · 2025
BrowseComp: a benchmark for browsing agents
| URL | https://openai.com/index/browsecomp/ |
|---|---|
| Topics | ReplicHAI / Agent Evals / 04 Web browsing & deep research |
| Tags | agent-eval |
Abstract
Measures: Hard browsing questions. Metric: Accuracy.
BibTeX
@misc{openai_browsecomp_2025,
title = {{BrowseComp}: a benchmark for browsing agents},
url = {https://openai.com/index/browsecomp/},
abstract = {Measures: Hard browsing questions. Metric: Accuracy.},
author = {{OpenAI}},
month = apr,
year = {2025},
keywords = {agent-eval},
}