Remote Code Execution Attack Success Rate on Codex
77.67C-F RateGPT-5.4 mini
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-5.4 miniFoundational LLM=GPT-5.4 mini2026.05 | 77.67 | 18.67 | 46.67 | |
| GLM-5Foundational LLM=GLM-52026.05 | 63 | 20 | 22.67 | |
| MiniMax-M2.7Foundational LLM=MiniMax-M2.72026.05 | 38 | 48.67 | 61.67 |