Spaces:
Sleeping
Sleeping
Multi-view-leaderboard
/
dataset
/Test Generation
/ComplexCodeEval-Python
/4
/QS
/token_counts_QS.csv
| Models, subset_0(122~225),subset_1(226~322),subset_2(345~571),subset_3(586~7038) | |
| StarCoder2-15b,26.21,25.31,22.31,23.79 | |
| CodeLlama-7b,24.57,28.22,26.47,26.65 | |
| CodeLlama-13b,30.95,22.86,27.72,24.83 | |
| CodeLlama-34b,28.46,27.89,24.06,28.03 | |
| DeepSeek-Coder-1.3b,24.09,26.57,26.00,25.83 | |
| DeepSeek-Coder-6.7b,24.78,25.51,24.96,22.99 | |
| DeepSeek-Coder-33b,29.04,29.32,28.66,29.12 | |