EVMBench Leaderboard — AI Smart Contract Auditors
testmachine.ai · 798 words · saved by 1 readers
117 vulnerabilities. 40 Code4rena audits. One scoreboard.
EVMBench Leaderboard — AI Smart Contract Auditors Home How It Works Token Custody Azimuth Leaderboard Blog Contact Launch App Open Benchmark · AI Security The EVMBench Leaderboard EVMBench is a standardized benchmark built by OpenAI for AI vulnerability detection on EVM smart contracts: 117 ground-truth vulnerabilities across 40 Code4rena audits . Vendors keep publishing one-off numbers. No one has put them on a single board — so we did. 40 Repositories 117 Vulnerabilities (120 at launch) 10 Published results # Model / Agent Detection Recall Found 1 Azimuth Our entry TestMachine Combined run a
saved by
related reading
- AuditAgentauditagent.nethermind.io
- evmbench.pdfcdn.openai.com
- Security incident disclosure — July 2026huggingface.co
- Measuring LLMs’ ability to develop exploits \ Anthropicred.anthropic.com
- Center for Responsible, Decentralized Intelligence at Berkeleyrdi.berkeley.edu
- Mythos finds a curl vulnerability | daniel.haxx.sedaniel.haxx.se
- FrontierSWEfrontierswe.com
- Senior SWE-Benchsenior-swe-bench.snorkel.ai
- Frontier AI Cybersecurity Observatorycybergym.io
- What Is a Smart Contract Security Audit?academy.binance.com
- AI agents find smart contract exploits \ Anthropicred.anthropic.com
- Rogue AI Trackerrogueaitracker.com