OpenAI and Paradigm, OtterSec release EVMbench, a benchmark test of 120 vulnerabilities based on 40 real audits for AI agent smart contract security. Claude Opus leads with a $37,824 discovery reward, OpenAI's OC-GPT-5.2 earns $31,623, and Gemini 3 Pro earns $25,112. #AI # Blockchain
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
OpenAI and Paradigm, OtterSec release EVMbench, a benchmark test of 120 vulnerabilities based on 40 real audits for AI agent smart contract security. Claude Opus leads with a $37,824 discovery reward, OpenAI's OC-GPT-5.2 earns $31,623, and Gemini 3 Pro earns $25,112. #AI # Blockchain