OpenAI and Paradigm Introduce EVMbench Ethereum Security Tool

EVMbench tests AI agents on detecting, patching, and exploiting Ethereum contract flaws.

  • OpenAI and Paradigm have launched EVMbench, a new tool to test AI agents on real Ethereum smart contract vulnerabilities.
  • The benchmark evaluates three critical modes: detecting, patching, and exploiting high-severity security flaws.
  • In exploit tests, the latest GPT-5.3-Codex scored 72.2%, more than doubling the performance of its predecessor.
  • The tool uses 120 curated vulnerabilities from 40 audits, with many sourced from open competitions like Code4rena and Tempo.

On February 18, 2026, OpenAI, in collaboration with investment firm Paradigm, introduced EVMbench, a groundbreaking tool designed to evaluate AI agents on Ethereum smart contract security. The Ethereum Virtual Machine test suite focuses on high-severity vulnerabilities as smart contract deployment reaches record highs. Consequently, the benchmark draws on 120 real-world vulnerabilities curated from 40 audits, including scenarios from the security process for Tempo.

- Advertisement -

Stripe launched the public testnet for its purpose-built blockchain, Tempo, in December with input from VISA, Shopify, and OpenAI. The goal is to ground testing in economically meaningful code, especially as AI-driven stablecoin payments expand. EVMbench tests agents across three distinct modes: detect, patch, and exploit. In the exploit phase, agents attempt end-to-end fund-draining attacks within a sandboxed environment.

Testing revealed that GPT-5.3-Codex achieved a 72.2% success rate in exploit mode, according to an OpenAI blog post. This significantly outperformed the 31.9% score of GPT-5, released six months earlier. However, performance was weaker in the detect and patch tasks, where agents sometimes failed to audit exhaustively.

Researchers cautioned that EVMbench does not fully capture real-world security complexity. Meanwhile, the weekly number of smart contracts deployed on Ethereum reached 669,500, according to Token Terminal. Measuring AI performance in such environments is now critical as models become powerful tools for both attackers and defenders.

✅ Follow BITNEWSBOT on Telegram, Facebook, LinkedIn, X.com, and Google News for instant updates.

- Advertisement -

Previous Articles:

- Advertisement -

Latest News

Bitcoin Holder Stress Hits 2018 Lows, Hinting at Bottom

Bitcoin’s “short-term holder stress” metric has reached its lowest level since the 2018 bear...

Apple’s Stock Lags Nasdaq as AI Delay Sparks Downgrades

Apple's stock correlation with the Nasdaq 100 has plummeted to its lowest level since...

Lagarde May Leave ECB Early Amid French Political Moves

Christine Lagarde is reportedly considering leaving the European Central Bank early, ahead of her...

Peter Thiel’s ETHZilla investment ends with massive losses

Peter Thiel has fully divested from ETHZilla, his ether-gobbling investment company.The company's shares have...

First Licensed DAO Governed Crypto Exchange Launches

DerivaDEX has launched a regulatory-first decentralized derivatives exchange under a Bermuda T license for...

Must Read

12 Hosting Providers To Buy VPS With Bitcoin: An Expert Guide for 2026

You need a VPS. You want to pay with Bitcoin. Simple enough, right?Not quite. The market for crypto VPS = VPS hosting that accepts...
🔥 #AD Get 20% OFF any new 12 month hosting plan from Hostinger. Click here!