List your company

Efficiency Test Generation on CodeContests Python

60ASR (Fast)STAB
25.232834.258943.28552.3111May 27, 2026

Evaluation results

MethodLinks
STABModel=Gemma-42026.056079.2379.84
STABModel=Gemini-3.12026.0559.2375.6577.84
STABModel=Qwen-3.52026.0556.1474.274.56
STABModel=GPT-5.42026.0556.0473.9174.81
BaseModel=GPT-5.42026.0551.8868.2168.05
BaseModel=Gemma-42026.0542.3265.841.77
BaseModel=Gemini-3.12026.0534.1154.8854.94
BaseModel=Qwen-3.52026.0526.5757.161.35