OpenAI Blog · Feb 18, 2026
Introducing EVMbench
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Introducing EVMbench. OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Introducing EVMbench' affects your current setup before relying on it in production.
ai