CyberGym-E2E: leaderboard

Metric: End-to-end success rate (%, stage S3) on the 920 OSS-Fuzz vulnerabilities (139 C/C++ projects) of the expanded benchmark: given only the codebase and build environment, the agent must write a PoC input that crashes the vulnerable build under a sanitizer, a patch that removes that crash, and keep the project functionality tests passing; with a $10 cost cap and a 90-minute limit per task; higher is better. Source: arxiv.org. Saturation forecast: Around June 2028. 3 models tracked.

Top models

#ModelScore
1GPT-5.465.9
2Gemini 3.1 Pro (Preview)43.8
3Claude Opus 4.637.9

Interactive version: theaggregate.ai/benchmark?slug=cybergym-e2e · How It Works · Data refreshed daily, snapshot 2026-09-29.