We present an extended version of SheetCopilotBench (https://doi.org/10.48550/arXiv.2305.19308), a benchmark dataset for evaluating large language models (LLMs) and code-generation systems on spreadsh
--- size_categories: - 100M<n<1B --- ### Dataset Summary This dataset is based on [olm/wikipedia](https://huggingface.co/datasets/olm/wikipedia). The main difference is that we add `Section::::` pref