{"url":"/sota/3d-question-answering-3d-qa-on-3d-mm-vet","task":{"name":"3D Question Answering (3D-QA)","url":"/task/3d-question-answering-3d-qa","note":null},"dataset":{"name":"3D MM-Vet","url":"/dataset/3d-mm-vet"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"A 3D-QA task requires models to answer a question when given all the information of a 3D scene. Here, models use the 3D spatial information, such as RGB-D scans or point cloud data. We also require models to specify the 3D-bounding boxes of objects that are related to this question answering. This prevents models from answering questions by relying on the textual priors of the trained questions without examining the scene. However, unlike 3D dense captioning, we do not require models to target one described object for each question. This is because multiple objects can be used to answer certain questions. For example, the question “What color is the chairs around the table?” is related to multiple objects. This question is also answerable as long as the chairs around the unique table in the scene have the same color. In such scenarios, we require models to answer the question addressing multiple 3D-bounding boxes.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Overall Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall Accuracy":"higher"}},"counts":{"rows":5,"rows_with_code":5,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ShapeLLM-13B","metrics":{"Overall Accuracy":"53.1"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/shapellm-universal-3d-object-understanding","paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","code":"https://github.com/qizekun/ShapeLLM","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ShapeLLM-7B","metrics":{"Overall Accuracy":"47.4"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/shapellm-universal-3d-object-understanding","paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","code":"https://github.com/qizekun/ShapeLLM","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PointLLM-13B v1.2","metrics":{"Overall Accuracy":"46.6"},"uses_additional_data":false,"paper_date":"2023-08-31","paper":"/paper/pointllm-empowering-large-language-models-to","paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","code":"https://github.com/openrobotlab/pointllm","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"PointLLM-7B v1.2","metrics":{"Overall Accuracy":"41.2"},"uses_additional_data":false,"paper_date":"2023-08-31","paper":"/paper/pointllm-empowering-large-language-models-to","paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","code":"https://github.com/openrobotlab/pointllm","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"Point-Bind & Point-LLM","metrics":{"Overall Accuracy":"23.5"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/point-bind-point-llm-aligning-point-cloud","paper_url":"https://arxiv.org/abs/2309.00615v1","paper_title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","code":"https://github.com/openrobotlab/pointllm","n_code_links":5,"syntology":{"n_ran":13,"n_unverified":7,"n_samples":20,"n_pointer_only_licence":7}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":15,"n_samples":37,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":31,"n_unverified":23,"n_samples":54,"n_pointer_only_licence":7,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}