Spaces:
Sleeping
Sleeping
Multi-view-leaderboard
/
dataset
/Test Generation
/ComplexCodeEval-Python
/5
/QS
/line_counts_QS.csv
| Models, subset_0(15~26),subset_1(27~40),subset_2(41~56),subset_3(56~95),subset_4(95~749) | |
| StarCoder2-15b,27.80,24.21,23.65,20.97,25.05 | |
| CodeLlama-7b,23.45,22.46,30.49,27.85,28.14 | |
| CodeLlama-13b,29.74,27.93,26.04,25.15,25.03 | |
| CodeLlama-34b,30.95,26.29,23.04,26.33,28.36 | |
| DeepSeek-Coder-1.3b,23.19,24.99,27.18,25.69,27.06 | |
| DeepSeek-Coder-6.7b,24.03,24.78,26.02,23.78,24.19 | |
| DeepSeek-Coder-33b,30.01,29.30,28.21,27.12,30.49 | |