NiniCat/MMLU-SR download history
NiniCat/MMLU-SR is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,332 times (201 in the last 7 days), and 103,654 times in total. It ranks #15,593 among datasets by monthly downloads.
MMLU-SR Dataset This is the dataset for the paper "MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models". Dataset Structure This dataset contains three different variants: Question Only: Key terms in questions are replaced with dummy words and