Efficiency-oriented Test Case Generation on CodeContests
75.82ASR (Mean)STAB
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| STABModel=Gemma-42026.05 | 75.82 | — | — | — | |
| STABModel=Gemini-3.12026.05 | 72.87 | — | — | — | |
| STABModel=Qwen-3.52026.05 | 71.07 | — | — | — | |
| STABModel=GPT-5.42026.05 | 70.83 | — | — | — | |
| BaseModel=GPT-5.42026.05 | 66.07 | — | — | — | |
| BaseModel=Qwen-3.52026.05 | 54.02 | — | — | — | |
| BaseModel=Gemini-3.12026.05 | 48.82 | — | — | — | |
| BaseModel=Gemma-42026.05 | 46.83 | — | — | — | |
| EvalPerfLLM Model=Gemini-3.12026.05 | — | 28.91 | 31.89 | 23.21 | |
| EvalPerfLLM Model=GPT-5.42026.05 | — | 45.35 | 47.84 | 42.06 | |
| STABLLM Model=Gemini-3.12026.05 | — | 73.68 | 75.44 | 69.48 | |
| STABLLM Model=GPT-5.42026.05 | — | 70.88 | 73.12 | 68.48 | |
| WEDGELLM Model=Gemini-3.12026.05 | — | 35.79 | 41.09 | 38.92 | |
| WEDGELLM Model=GPT-5.42026.05 | — | 29 | 36.18 | 37.81 |