Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
Introducing EVMbench
OpenAI and Paradigm introduce EVMbench, a benchmark for evaluating AI agents on detecting, patching, and exploiting high-severity smart contract vulnerabilities.
From the source
OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.
openai.com
Visit source ↗openai.com
- Announced
- 18 Feb 2026 00:00 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+166d after)