ExploitGym (version unspecified; 6h timeout): leaderboard
Metric: Successful intended exploits (#); version unspecified; 6h timeout. Source: www.cybergym.io. Saturation forecast: Around May 2028. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Mythos 5 | 247 |
| 2 | Claude Opus 5 | 191 |
| 3 | Claude Opus 4.8 | 120 |
Interactive version: theaggregate.ai/benchmark?slug=exploitgym-version-unspecified-6h-timeout · How It Works · Data refreshed daily, snapshot 2026-10-09.