ExploitGym (v1; 6h timeout): leaderboard
Metric: Successful intended exploits (#); v1; 6h timeout. Source: www.cybergym.io. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Thinking, Max) (Codex CLI) | 293 |
Interactive version: theaggregate.ai/benchmark?slug=exploitgym-v1-6h-timeout · How It Works · Data refreshed daily, snapshot 2026-10-09.