From the source

BrowseComp: a benchmark for browsing agents

OpenAI introduces BrowseComp, a benchmark for evaluating browsing agents.

Research paper

From the source
BrowseComp: a benchmark for browsing agents.
openai.com

Other stories

OpenAI· 16 Oct

OpenAI· 15 Oct

Sullivan & Cromwell builds Agreement Analyzer with OpenAI

SentinelOne cuts malware analysis from weeks to hours
SentinelOne uses OpenAI Daybreak to speed reverse engineering from weeks to hours.

OpenAI

· 14 Oct

OpenAI· 14 Oct

Block uses OpenAI Daybreak to speed security operations

OpenAI· 14 Oct

OpenAI· 14 Oct