CyScenarioBench A

AI benchmark · Cybersecurity

Built by
Irregular
Tier
A why
Snapshot

Open benchmark ↗irregular.com/research/assessing-gpt-6-cyber-against-offensi…

The same benchmark as CyScenarioBench solved, listed under another name.

What is CyScenarioBench?

CyScenarioBench measures how well AI models plan and execute multi-stage offensive cybersecurity operations over long horizons, reported as average success rate and scenarios solved at least once.

Who built CyScenarioBench

Led by Irregular.

    Tier A

    A

    Widely used: a lab reports it, or 50 or more models are scored on it.

    How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

    • 2 models scored
    • reported by OpenAI
    • in curated RL directories (1 pt)

    On X · well regarded, moderate buzz, from 5 posts about CyScenarioBench in the last month

    Cited in Anthropic's Mythos 5.2 launch results and repeated in benchmark roundups; Irregular also reports open-weight results, but there is little independent discussion.

    @Irregular ↗ · @Irregular ↗ · @TekonBurns ↗

    How we got to tier A
    1. Adoption: 2 models scored; reported by OpenAI. Tier A.
    2. On X: well regarded, moderate buzz. “Cited in Anthropic's Mythos 5.2 launch results and repeated in benchmark roundups; Irregular also reports open-weight results, but there is little independent discussion.” No move.
    3. In curated RL directories: 1 point, a floor of none.
    4. Confirmed: a line from its own site or paper places it.

    A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

    Where CyScenarioBench sits

    Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map

    The galaxy could not load. See every vendor on the board.

    Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-16 snapshot.