Efficiency Test Generation on CodeContests C++
62.22ASR (Fast)STAB
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| STABModel=Gemma-42026.05 | 62.22 | 71.78 | 76.76 | |
| STABModel=GPT-5.42026.05 | 60.3 | 66.59 | 71.83 | |
| STABModel=Qwen-3.52026.05 | 59.33 | 69.11 | 72.27 | |
| STABModel=Gemini-3.12026.05 | 58.52 | 67.11 | 73.93 | |
| BaseModel=Gemma-42026.05 | 58.07 | 64.52 | 41.16 | |
| BaseModel=GPT-5.42026.05 | 53.85 | 61.63 | 66.03 | |
| BaseModel=Qwen-3.52026.05 | 34.74 | 57.19 | 62.69 | |
| BaseModel=Gemini-3.12026.05 | 32.22 | 42.52 | 43.33 |