Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Ferretgithub.com · Low evidenceFerret is an automated red teaming framework that generates adversarial prompts to test the safety of large language models. It improves attack success rates by 46% over Rainbow Teaming while reducing the time needed to achieve 90% attack success by 15.2%.
Parse Score