List your company

End-to-end penetration testing on PentestGPT Ben 13 machines

12Machines RootedPENTESTGPT V2
4.726.618.510.39Feb 19, 2026

Evaluation results

MethodLinks
PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Thinking2026.0212
PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Thinking2026.0212
PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Standard2026.0211
PENTESTGPT V2Model=Gemini 3, Thinking Mode=Thinking2026.0211
PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Standard2026.0210
PENTESTGPT V2Model=Gemini 3, Thinking Mode=Standard2026.0210
PentestAgentModel=GPT-5.2, Thinking Mode=Thinking2026.029
PentestAgentModel=Opus 4.5, Thinking Mode=Thinking2026.029
VulnBotModel=GPT-5.2, Thinking Mode=Thinking2026.029
VulnBotModel=Opus 4.5, Thinking Mode=Thinking2026.029
PentestGPTModel=GPT-5.2, Thinking Mode=Thinking2026.028
AutoPTModel=Opus 4.5, Thinking Mode=Thinking2026.028
PentestAgentModel=GPT-5.2, Thinking Mode=Standard2026.028
PentestAgentModel=Gemini 3, Thinking Mode=Thinking2026.028
VulnBotModel=GPT-5.2, Thinking Mode=Standard2026.028
VulnBotModel=Opus 4.5, Thinking Mode=Standard2026.028
VulnBotModel=Gemini 3, Thinking Mode=Thinking2026.028
PentestGPTModel=GPT-5.2, Thinking Mode=Standard2026.027
PentestGPTModel=Opus 4.5, Thinking Mode=Thinking2026.027
PentestGPTModel=Gemini 3, Thinking Mode=Thinking2026.027
AutoPTModel=GPT-5.2, Thinking Mode=Thinking2026.027
AutoPTModel=Opus 4.5, Thinking Mode=Standard2026.027
PentestAgentModel=Opus 4.5, Thinking Mode=Standard2026.027
PentestAgentModel=Gemini 3, Thinking Mode=Standard2026.027
PentestGPTModel=Opus 4.5, Thinking Mode=Standard2026.026
PentestGPTModel=Gemini 3, Thinking Mode=Standard2026.026
AutoPTModel=GPT-5.2, Thinking Mode=Standard2026.026
AutoPTModel=Gemini 3, Thinking Mode=Thinking2026.026
VulnBotModel=Gemini 3, Thinking Mode=Standard2026.026
AutoPTModel=Gemini 3, Thinking Mode=Standard2026.025