build1 distinct publisher
ExploitGym grades agents on the step from crash input to working exploit
The benchmark hands an agent an input that already crashes a program and asks it to escalate to file access or code execution. Claude Mythos Preview managed 157 of 898 instances, with model safeguards disabled.
Publishers:arxiv.org
Reality
- Evidence55
- Adoption12
- Hype gap+18
- Incentives55