Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models竞赛任务及可选子任务提示下的网络能力。核对原文署名 ↗
BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems围绕真实代码库中的漏洞生命周期,分别评测发现、利用和修补任务。核对原文署名 ↗