SEC-bench
EvalsBenchmark / dataset
Real-world vuln reproduction and patching tasks for agents.
- Category
- Cyber offense capability
- Insurance exposure
- Breach/cyber
- Publisher
- Academic (SEC-bench team)
- Publisher type
- Academic
- License
- MIT
- Status
- Maintained (<12mo)
- Last commit
- 2026-01-27
- Stars
- 101
Wanich Risk Lab, 2026.