BrowseComp: a benchmark for browsing agents

1 year ago 38
BrowseComp: a benchmark for browsing agents.
Read Entire Article
  1. Homepage
  2. OpenAI
  3. BrowseComp: a benchmark for browsing agents

Related

A $50 million fund to build with communities

A $50 million fund to build with communities

1 year ago 72
Invideo AI uses OpenAI models to create videos 10x faster

Invideo AI uses OpenAI models to create videos 10x faster

1 year ago 64
ChatGPT agent System Card

ChatGPT agent System Card

1 year ago 62