{"url":"/dataset/mmcode","name":"MMCode","full_name":null,"description_markdown":"MMCode is a multi-modal code generation dataset designed to evaluate the problem-solving skills of code language models in visually rich contexts (i.e. images). It contains 3,548 questions paired with 6,620 images, derived from real-world programming challenges across 10 code competition websites, with Python solutions and tests provided. The dataset emphasizes the extreme demand for reasoning abilities, the interwoven nature of textual and visual contents, and the occurrence of questions containing multiple images.","description_withheld":null,"homepage":"https://huggingface.co/datasets/likaixin/MMCode","introduced_date":"2024-04-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/mmcode-evaluating-multi-modal-code-large","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","first_author":"Kaixin Li","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Code Completion","url":"/task/code-completion","datasets_with_task":"/datasets/task/code-completion"},{"name":"Python Code Synthesis","url":"/task/python-code-synthesis","datasets_with_task":"/datasets/task/python-code-synthesis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MMCode"],"data_loaders":[],"num_papers_in_archive":3,"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."}