Palisade InterCode-CTF agents
EvalsTool (not an eval — tooling/reference entry)
Shows plain agents reach 95% on InterCode-CTF; argues CTF evals are saturated.
- Category
- Cyber offense capability
- Insurance exposure
- Breach/cyber
- Publisher
- Palisade Research
- Publisher type
- Nonprofit / research org
- License
- MIT
- Status
- Stale (>12mo)
- Last commit
- 2024-12-05
- Stars
- 71
Wanich Risk Lab, 2026.