[KongchangAI]
Benchmark

ExploitBench

评估AI模型发现和利用软件漏洞能力的网络安全基准测试

Timeline (last 90 days)

Oct 15

Meta reports that Muse Wonder's cyber capabilities are 88.4% on CyberGym, 58.9% on ExploitBench, and 92 captured flags on ExploitGym.

Unverified50%
Sep 12

The GPT-6 Astra leak claims a perfect score of 100% on ExploitBench.

Expired50%

All Facts (1)

Source Articles