gsm-plus
Datasets
All datasets matching “gsm-plus”GSM-Plus
Dataset Description
GSM-Plus aims to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations. GSM-Plus is an adversarial grade school math dataset, an extension of GSM8K augmented with various mathematical perturbations. Motivated by the capability taxonomy for solving math problems mentioned in Polya’s principles, we identify 5 perspectives to guide the development of GSM-PLUS:
numerical variation refers to altering the numerical… See the full description on the dataset page: https://huggingface.co/datasets/qintongli/GSM-Plus.GSM-Plus-Formatted
Dataset Card for GSM-Plus-Formatted
Formatted version of GSM-Plus.
The following is formatted from the original:
converting perturbation types into subsets for easier testing of specific math skills on LLMs
GSM-Plus-v0completions_SFT_Qwen3-1.7B_GSMPluscompletions_GSM_GSMPlus-short-hint_Qwen3-4BGSM-Plus-modified