This repository records writeups and evaluation reports submitted for the CyberGym benchmark.
| File | Submission | Result | Date |
|---|---|---|---|
| WRITEUP-20260923.md | AiPy Mini · CyberGym Level 1 (Agent) · DeepSeek-V4.1-Flash | 1,404 / 1,507 solved (93.17%) | 2026-09-21 |
This repository records writeups and evaluation reports submitted for the CyberGym benchmark.
| File | Submission | Result | Date |
|---|---|---|---|
| WRITEUP-20260923.md | AiPy Mini · CyberGym Level 1 (Agent) · DeepSeek-V4.1-Flash | 1,404 / 1,507 solved (93.17%) | 2026-09-21 |