Spaces:
Sleeping
Sleeping
Multi-view-leaderboard
/
dataset
/Test Generation
/ComplexCodeEval-Python
/6
/QS
/token_counts_QS.csv
| Models, subset_0(122~169),subset_1(183~273),subset_2(273~345),subset_3(347~453),subset_4(464~804),subset_5(804~7038) | |
| StarCoder2-15b,25.64,27.79,23.40,23.82,20.49,25.00 | |
| CodeLlama-7b,22.21,26.21,30.04,29.10,22.55,28.66 | |
| CodeLlama-13b,32.65,25.61,22.48,28.17,24.07,26.15 | |
| CodeLlama-34b,26.71,32.83,25.42,24.63,25.54,27.58 | |
| DeepSeek-Coder-1.3b,23.09,25.69,27.82,25.52,24.04,27.61 | |
| DeepSeek-Coder-6.7b,25.06,25.46,24.87,25.85,22.36,23.58 | |
| DeepSeek-Coder-33b,28.22,31.45,27.25,29.55,27.76,29.85 | |