Code Reasoning on BigCodeBench
40BigCodeBench ScoreQwen2.5-Coder-ScaleQuest
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-Coder-ScaleQuest# Samples (K)=156, Base Model=Qwen2.5-Coder-7B-Base2024.10 | 40 | 69.9 | |
| Qwen2.5-Coder-CFB-Aug# Samples (K)=156, Base Model=Qwen2.5-Coder-7B-Base2024.10 | 39 | 69.3 | |
| Qwen2.5-Coder-CFB# Samples (K)=156, Base Model=Qwen2.5-Coder-7B-Base2024.10 | 35.6 | 64 |