Spaces:
Sleeping
Sleeping
Multi-view-leaderboard
/
dataset
/Test Generation
/ComplexCodeEval-Python
/8
/QS
/token_counts_QS.csv
| Models, subset_0(122~162),subset_1(162~226),subset_2(237~279),subset_3(280~347),subset_4(351~425),subset_5(430~586),subset_6(610~886),subset_7(896~7038) | |
| StarCoder2-15b,27.70,24.46,27.81,21.71,24.47,21.86,22.09,24.47 | |
| CodeLlama-7b,22.14,26.22,26.55,29.38,28.63,25.69,26.15,27.22 | |
| CodeLlama-13b,31.23,30.24,21.43,25.45,27.93,27.21,22.43,26.98 | |
| CodeLlama-34b,27.71,28.97,31.50,23.61,23.51,25.10,28.47,27.66 | |
| DeepSeek-Coder-1.3b,21.46,27.43,24.93,28.16,25.51,25.82,24.65,27.07 | |
| DeepSeek-Coder-6.7b,26.18,23.26,25.55,25.35,26.38,23.48,22.43,23.69 | |
| DeepSeek-Coder-33b,29.25,28.76,31.47,26.92,27.73,29.55,27.07,31.42 | |