Efficiency Test Generation on CodeContests Python
60ASR (Fast)STAB
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| STABModel=Gemma-42026.05 | 60 | 79.23 | 79.84 | |
| STABModel=Gemini-3.12026.05 | 59.23 | 75.65 | 77.84 | |
| STABModel=Qwen-3.52026.05 | 56.14 | 74.2 | 74.56 | |
| STABModel=GPT-5.42026.05 | 56.04 | 73.91 | 74.81 | |
| BaseModel=GPT-5.42026.05 | 51.88 | 68.21 | 68.05 | |
| BaseModel=Gemma-42026.05 | 42.32 | 65.8 | 41.77 | |
| BaseModel=Gemini-3.12026.05 | 34.11 | 54.88 | 54.94 | |
| BaseModel=Qwen-3.52026.05 | 26.57 | 57.1 | 61.35 |