Part of the benchmark canon: 2 entries, all measure the model. How to read the Paladin column is defined on the canon page.
| Benchmark | Organization | Measures | Paladin |
|---|---|---|---|
| CyberSecEval (Purple Llama) (top 12) | Meta | Umbrella suite: insecure code, injection, interpreter abuse | Measures the model |
| SusVibes | Academic | Vulnerability of agent-generated code on real tasks | Measures the model |
Previous: Cyber defense and threat intel. Next: Jailbreak and refusal.