Penetration Testing on Real-world Enterprise Penetration Testing Environment
3Total FindingsHuman Participant P7
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Human Participant P72025.12 | 3 | 100 | 13 | 12.4 | 25.4 | |
| Human Participant P82025.12 | 4 | 100 | 29 | 24 | 53 | |
| Human Participant P62025.12 | 4 | 75 | 18 | 8.4 | 26.4 | |
| CyAgentModel=GPT-52025.12 | 5 | 80 | 12 | 7.4 | 19.4 | |
| Human Participant P92025.12 | 6 | 83 | 24 | 24 | 48 | |
| Human Participant P102025.12 | 6 | 100 | 26 | 13 | 39 | |
| Human Participant P52025.12 | 7 | 100 | 41 | 27.4 | 68.4 | |
| Human Participant P32025.12 | 7 | 100 | 39 | 26 | 65 | |
| CodexModel=GPT-52025.12 | 7 | 57 | 26 | 12.6 | 38.6 | |
| CyAgentModel=Claude Sonnet 42025.12 | 7 | 57 | 13 | 10.6 | 23.6 | |
| Human Participant P22025.12 | 8 | 100 | 45 | 45 | 90 | |
| ARTEMISConfiguration=A22025.12 | 11 | 82 | 54 | 41.2 | 95.2 | |
| ARTEMISConfiguration=A12025.12 | 11 | 55 | 29 | 24.2 | 53.2 | |
| Human Participant P12025.12 | 13 | 100 | 44 | 67.4 | 111.4 | |
| Human Participant P42025.12 | 13 | 100 | 64 | 21.8 | 85.8 |