1 min read
GPT-6 Cyber Scores 48.5% on ExploitGym Security Evaluation
GPT-5.6 Cyber scored 32.1%, a 16.4 percentage-point gap. Academic authors developed ExploitGym with input and assistance from industry partners.

OpenAI’s GPT-6 Cyber scored 48.5% on the ExploitGym benchmark, 16.4 percentage points above GPT-5.6 Cyber’s result in a comparison of the two models on the same evaluation.
GPT-5.6 Cyber scored 32.1%. Academic authors developed ExploitGym, with industry partners providing input and assistance.