HyperAI超神经

Code Generation On Dseval Leetcode

评估指标

Pass Rate
w/o Intact
w/o PE

评测结果

各个模型在此基准测试上的表现结果

模型名称
Pass Rate
w/o Intact
w/o PE
Paper TitleRepository
CoML42.542.562.5MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
Code Interpreter API45.045.055.0--
ChatDev32.532.550.0--
Chapyter45.045.060.0--
Jupyter-AI57.557.570.0--
0 of 5 row(s) selected.