{"url":"/dataset/rmcbench","name":"RMCBench","full_name":null,"description_markdown":"The first benchmark comprising 473 prompts designed to assess the ability of LLMs to resist malicious code generation.","description_withheld":null,"homepage":"https://huggingface.co/datasets/zhongqy/RMCBench","introduced_date":"2024-09-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/rmcbench-benchmarking-large-language-models","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","first_author":"Jiachi Chen","url":null},"license":{"name":"arXiv perpetual, non-exclusive license","url":"https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RMCBench"],"data_loaders":[{"repo":"https://github.com/qing-yuan233/RMCBench","url":"https://huggingface.co/datasets/zhongqy/RMCBench","frameworks":[]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}