smart contracts

Hold

Techniques

Self-executing blockchain programs used to encode on-chain logic and rules.

Why it's here

Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.

Evidence (1)

7OpenAI Blog·2/18/2026research
OpenAI and Paradigm Launch EVMbench
OpenAI and Paradigm introduced EVMbench, a benchmark for evaluating AI agents on detecting, patching, and exploiting high-severity smart contract vulnerabilities. The benchmark is designed to measure how well models handle security tasks in Ethereum Virtual Machine-based environments.