{"url":"/dataset/3d-mm-vet","name":"3D MM-Vet","full_name":null,"description_markdown":"We established a 3D evaluation benchmark, 3D MM-Vet, to assess the 4-level capacity in embodied interaction scenarios, varying from basic perception to control statements generation.","description_withheld":null,"homepage":"https://github.com/qizekun/ShapeLLM","introduced_date":"2024-02-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","first_author":"Zekun Qi","url":null},"license":{"name":"CC By NC 4.0","url":"https://github.com/tatsu-lab/stanford_alpaca/blob/main/DATA_LICENSE"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"}],"tasks":[{"name":"3D Question Answering (3D-QA)","url":"/task/3d-question-answering-3d-qa","datasets_with_task":"/datasets/task/3d-question-answering-3d-qa"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["3D MM-Vet"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-question-answering-3d-qa-on-3d-mm-vet","task":"3D Question Answering (3D-QA)","dataset_variant":"3D MM-Vet","rows":5,"metrics":["Overall Accuracy"],"first_row_in_archive_order":{"model":"ShapeLLM-13B","paper":"/paper/shapellm-universal-3d-object-understanding","metrics":{"Overall Accuracy":"53.1"},"code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":9,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":13,"samples_unverified":7,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointllm-empowering-large-language-models-to","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","date":"2023-08-31","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":37,"samples_ran":22,"samples_unverified":15,"pointer_only_for_licence":7,"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."}