ai-safety-institute/AgentHarm download history

ai-safety-institute/AgentHarm is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 15,237 times (3,173 in the last 7 days), and 95,796 times in total. It ranks #2,700 among datasets by monthly downloads.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Maksym Andriushchenko1,†,*, Alexandra Souly2,* Mateusz Dziemian1, Derek Duenas1, Maxwell Lin1, Justin Wang1, Dan Hendrycks1,§, Andy Zou1,¶,§, Zico Kolter1,¶, Matt Fredrikson1,¶,* Eric Winsor2, Jerome Wynne2, Yarin Gal2,♯

Spaces using AgentHarm

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1815,237+57%
October 20269,713+26%
September 20267,725+52%
August 20265,089+32%
July 20263,858-0%
June 20263,862+9%
May 20263,527-36%
April 20265,485+15%
March 20264,771-5%
February 20265,033-6%
January 20265,342-14%
December 20256,218+161%

Its busiest 30 days so far ended on 2026-11-14, with 15,337 downloads.

Open ai-safety-institute/AgentHarm on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.