ExploitGym (pass@1)Browse 296

ExploitGym (pass@1)

Can the model diagnose or complete difficult cybersecurity tasks?

Version not specifiedExact reported variant
Cybersecurity3 ranked models3 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

3
RankModelBest scoreBest reported setting
1GPT-5.5OpenAI14.8%xhigh effortMeta report1 value · 1 reportJul 9, 2026 · source
2Gemini 3.1 ProGoogle1.4%high effortMeta report1 value · 1 reportJul 9, 2026 · source
3Muse Spark 1.1Meta0.8%xhigh effortMeta report1 value · 1 reportJul 9, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model diagnose or complete difficult cybersecurity tasks?

Security analysis or exploitation under a controlled evaluation environment. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

Pass@1.

Method / source