BoxPwnr traces and benchmark results across multiple security platforms.
Each trace includes the full LLM interaction, commands executed, a markdown report + attack graph, stats and config used. Browse leaderboards, replay runs in an interactive web viewer, and read AI-generated reports:
| Platform | Solved | Completion | Traces |
|---|---|---|---|
| HTB Labs | 218/521 |  |
691 |
| HTB Starting Point | 25/25 |  |
770 |
| HTB Challenges | 126/818 |  |
242 |
| PortSwigger Labs | 163/270 |  |
377 |
| XBOW | 101/104 |  |
527 |
| Cybench | 40/40 | |
1148 |
| picoCTF | 363/439 |  |
1045 |
| TryHackMe | 87/466 |  |
514 |
| HackBench | 11/16 |  |
34 |
| LevelUpCTF | 50/255 |  |
166 |
| Neurogrid CTF: The ultimate AI security showdown | 17/36 |  |
197 |