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
- Model Pulse 8 likes
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 15,237 | +57% |
| October 2026 | 9,713 | +26% |
| September 2026 | 7,725 | +52% |
| August 2026 | 5,089 | +32% |
| July 2026 | 3,858 | -0% |
| June 2026 | 3,862 | +9% |
| May 2026 | 3,527 | -36% |
| April 2026 | 5,485 | +15% |
| March 2026 | 4,771 | -5% |
| February 2026 | 5,033 | -6% |
| January 2026 | 5,342 | -14% |
| December 2025 | 6,218 | +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.