CyScenarioBench — leaderboard
Irregular scenario-based offensive security benchmark measuring whether agents can plan and complete full multi-stage attack scenarios in realistic environments.
Metric: Average Success Rate (%). Source: epochai.substack.com. Status: saturation imminent. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Mythos 5 | 36.7 |
| 2 | Claude Mythos Preview | 29.2 |
| 3 | GPT-5.5 | 26 |
| 4 | Claude Opus 4.8 | 16.6 |
| 5 | GPT-5.4 | 9 |
| 6 | GPT-5.2 | 0 |
| 7 | Gemini 3 Pro | 0 |
| 8 | Muse Spark | 0 |
| 9 | GPT-5.3 Codex | 0 |
Interactive version: theaggregate.ai/benchmark?slug=cyscenariobench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.