Hugging Face· PlatformStory of the weekCapability change

Our Transformers Code Agent beats the GAIA benchmark 🏅

Hugging Face's Transformers Code Agent achieved top performance on the GAIA benchmark, using a code agent approach with tools for web browsing and file inspection. The post also announces the upgrade of the Transformers Agents library to the standalone smolagents library.

From the source

After some experiments, we were impressed by the performance of Transformers Agents to build agentic systems, so we wanted to see how good it was! We tested using a Code Agent built with the library on the GAIA benchmark, arguably the most difficult and comprehensive agent benchmark… and ended up on top!

huggingface.co