jintailin/

SE-Bench

The SE-Bench contains the following subsets (configurations). Please note that all data is loaded under the train split key regardless of the subset.

train: train train set single_test: single function test set multiple_test: multiple function test set

You can load different parts of the benchmark by specifying the configuration name.

from datasets import load_dataset

dataset = load_dataset("jintailin/SE-Bench"… See the full description on the dataset page: https://huggingface.co/datasets/jintailin/SE-Bench.