# Introducing EVMbench

DevFeed: [Introducing EVMbench](<https://devfeed.tech/articles/introducing-evmbench-6486.md>)

Original publisher: [Read original article](<https://openai.com/index/introducing-evmbench>)

Published: 2026-02-18T00:00:00Z

Content type: article

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Blockchain](<https://devfeed.tech/topics/blockchain.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Security](<https://devfeed.tech/topics/security.md>), [Code](<https://devfeed.tech/topics/code.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [audits](<https://devfeed.tech/tags/audits.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blockchain](<https://devfeed.tech/tags/blockchain.md>), [code](<https://devfeed.tech/tags/code.md>), [openai](<https://devfeed.tech/tags/openai.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

## AI overview

OpenAI and Paradigm introduce EVMbench, a benchmark that evaluates AI agents on detecting, patching, and exploiting high-severity smart contract vulnerabilities. It uses curated audit cases and sandboxed blockchain environments to measure these capabilities through automated grading and exploit checks.

## Source excerpt

OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents' ability to detect, patch, and exploit high-severity smart contract vulnerabilities.