EVMbench
AssessTools
A benchmark for testing AI agents on smart contract vulnerability detection, patching, and exploitation.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by security coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7OpenAI Blog·2/18/2026securityOpenAI and Paradigm Launch EVMbench
OpenAI and Paradigm introduced EVMbench, a benchmark designed to evaluate AI agents on identifying, patching, and exploiting high-severity smart contract vulnerabilities. The benchmark focuses on agent performance in blockchain security tasks involving the Ethereum Virtual Machine ecosystem.