ExploitGym (v1; 4h timeout): leaderboard
Metric: Successful intended exploits (#); v1; 4h timeout. Source: www.cybergym.io. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.1 (Helpful-only) | 7 |
Interactive version: theaggregate.ai/benchmark?slug=exploitgym-v1-4h-timeout · How It Works · Data refreshed daily, snapshot 2026-10-09.