Malicious GitHub Repository Exploitation on Malicious GitHub Repository Exploitation D_repo (test)
94.99ASRGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.02 | 94.99 | |
| Grok-42026.02 | 94.44 | |
| Qwen3-max2026.02 | 94.14 | |
| Qwen3-235B-A22B-Thinking-2507Model Type=MoE, Mode=Thinking2026.02 | 94.14 | |
| GLM-4.72026.02 | 93.31 | |
| Seed-OSS-36B-Instruct2026.02 | 88.97 | |
| Doubao-seed-1-8-2512282026.02 | 88.35 | |
| Kimi-K2-Instruct-09052026.02 | 88.24 | |
| Claude Sonnet 4.5Mode=Thinking2026.02 | 86.19 | |
| GPT-5.2-2025-12-112026.02 | 83.74 | |
| MiniMax-M2.12026.02 | 82.11 |