Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
AVID (AVIDML)avidml.org · Low evidenceAVID is an open source knowledge base that catalogs failure modes for general purpose AI systems, including generative models and developer tools. It maintains a high-fidelity database of vulnerabilities with reproducible evaluation details and maps failures to a library of taxonomies.
Parse Score