New benchmark evaluates AI agents' ability to detect, patch, and exploit smart contract vulnerabilities. GPT-5.3-Codex scores 72.2% on exploit tasks.
OpenAI and Paradigm Launch EVMbench to Test AI Smart Contract Hacking
1 month ago New benchmark evaluates AI agents' ability to detect, patch, and exploit smart contract vulnerabilities. GPT-5.3-Codex scores 72.2% on exploit tasks.
Related
Is Polymarket a threat to democracy?
2 hours ago
