End-to-end penetration testing on PentestGPT Ben 13 machines
12Machines RootedPENTESTGPT V2
Evaluation Results
| Method | Links | |
|---|---|---|
| PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Thinking2026.02 | 12 | |
| PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Thinking2026.02 | 12 | |
| PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Standard2026.02 | 11 | |
| PENTESTGPT V2Model=Gemini 3, Thinking Mode=Thinking2026.02 | 11 | |
| PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Standard2026.02 | 10 | |
| PENTESTGPT V2Model=Gemini 3, Thinking Mode=Standard2026.02 | 10 | |
| PentestAgentModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 9 | |
| PentestAgentModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 9 | |
| VulnBotModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 9 | |
| VulnBotModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 9 | |
| PentestGPTModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 8 | |
| AutoPTModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 8 | |
| PentestAgentModel=GPT-5.2, Thinking Mode=Standard2026.02 | 8 | |
| PentestAgentModel=Gemini 3, Thinking Mode=Thinking2026.02 | 8 | |
| VulnBotModel=GPT-5.2, Thinking Mode=Standard2026.02 | 8 | |
| VulnBotModel=Opus 4.5, Thinking Mode=Standard2026.02 | 8 | |
| VulnBotModel=Gemini 3, Thinking Mode=Thinking2026.02 | 8 | |
| PentestGPTModel=GPT-5.2, Thinking Mode=Standard2026.02 | 7 | |
| PentestGPTModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 7 | |
| PentestGPTModel=Gemini 3, Thinking Mode=Thinking2026.02 | 7 | |
| AutoPTModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 7 | |
| AutoPTModel=Opus 4.5, Thinking Mode=Standard2026.02 | 7 | |
| PentestAgentModel=Opus 4.5, Thinking Mode=Standard2026.02 | 7 | |
| PentestAgentModel=Gemini 3, Thinking Mode=Standard2026.02 | 7 | |
| PentestGPTModel=Opus 4.5, Thinking Mode=Standard2026.02 | 6 | |
| PentestGPTModel=Gemini 3, Thinking Mode=Standard2026.02 | 6 | |
| AutoPTModel=GPT-5.2, Thinking Mode=Standard2026.02 | 6 | |
| AutoPTModel=Gemini 3, Thinking Mode=Thinking2026.02 | 6 | |
| VulnBotModel=Gemini 3, Thinking Mode=Standard2026.02 | 6 | |
| AutoPTModel=Gemini 3, Thinking Mode=Standard2026.02 | 5 |