0

Browsecomp RL Env (Prime Intellect)

Fresh

BrowseComp evaluation environment

Type
RL Env
Publisher
Prime Intellect
Tags
Tool UseWeb Search
Runtime
tool-use
License
unknown
Size
v0.1.6
Published
Sep 2025
Canonical
app.primeintellect.ai/dashboard/environments/primeintellect/browsecomp

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →

Evals this tool implements

2

Same problem set, this tool's harness. Run it to score a model on the test.

BrowseComp

OpenAI

1,266 hard fact-finding questions on the open web requiring persistent browsing and reasoning over scattered, obscure sources.

ActiveBrowser UseRetrievalPlanningAgentic

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

OpenAI

A benchmark for evaluating agents' ability to browse the web. The dataset consists of challenging questions that generally require web-access to answer correctly.

ActiveAssistants