Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Irregular is a frontier AI security lab dedicated to protecting the world from increasingly capable and sophisticated AI systems. The company conducts offensive security assessments of advanced AI models, such as GPT 5.5 and Meta's Muse Spark, and is trusted by leading AI labs.
Parse Score