{"url":"/sota/robot-manipulation-on-calvin","task":{"name":"Robot Manipulation","url":"/task/robot-manipulation","note":null},"dataset":{"name":"CALVIN","url":"/dataset/calvin-composing-actions-from-language-and"},"category":"Robots","categories":["Robots"],"category_note":null,"description":null,"description_from":null,"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":["avg. sequence length (D to D)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"avg. sequence length (D to D)":null}},"counts":{"rows":19,"rows_with_code":13,"rows_with_paper_page":19,"rows_dated":19,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DreamVLA","metrics":{"avg. sequence length (D to D)":"4.44"},"uses_additional_data":false,"paper_date":"2025-07-06","paper":"/paper/dreamvla-a-vision-language-action-model-1","paper_url":"https://arxiv.org/abs/2507.04447v2","paper_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","code":"https://github.com/Zhangwenyao1/DreamVLA","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"VPP","metrics":{"avg. sequence length (D to D)":"4.29"},"uses_additional_data":false,"paper_date":"2024-12-19","paper":"/paper/video-prediction-policy-a-generalist-robot","paper_url":"https://arxiv.org/abs/2412.14803v2","paper_title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","code":"https://github.com/roboterax/video-prediction-policy","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"RoboVLMs","metrics":{"avg. sequence length (D to D)":"4.25"},"uses_additional_data":false,"paper_date":"2024-12-18","paper":"/paper/towards-generalist-robot-policies-what","paper_url":"https://arxiv.org/abs/2412.14058v3","paper_title":"Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models","code":"https://github.com/Robot-VLAs/RoboVLMs","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Openhelix","metrics":{"avg. sequence length (D to D)":"4.08"},"uses_additional_data":false,"paper_date":"2025-05-06","paper":"/paper/openhelix-a-short-survey-empirical-analysis","paper_url":"https://arxiv.org/abs/2505.03912v1","paper_title":"OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation","code":"https://github.com/OpenHelix-robot/OpenHelix","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"UP-VLA","metrics":{"avg. sequence length (D to D)":"4.08"},"uses_additional_data":false,"paper_date":"2025-01-31","paper":"/paper/up-vla-a-unified-understanding-and-prediction","paper_url":"https://arxiv.org/abs/2501.18867v2","paper_title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"GR-MG","metrics":{"avg. sequence length (D to D)":"4.04"},"uses_additional_data":false,"paper_date":"2024-08-26","paper":"/paper/gr-mg-leveraging-partially-annotated-data-via","paper_url":"https://arxiv.org/abs/2408.14368v2","paper_title":"GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy","code":"https://github.com/bytedance/GR-MG","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"MoDE","metrics":{"avg. sequence length (D to D)":"4.01"},"uses_additional_data":false,"paper_date":"2024-12-17","paper":"/paper/efficient-diffusion-transformer-policies-with","paper_url":"https://arxiv.org/abs/2412.12953v1","paper_title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","code":"https://github.com/intuitive-robots/MoDE_Diffusion_Policy","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"RoboUniView","metrics":{"avg. sequence length (D to D)":"3.855"},"uses_additional_data":false,"paper_date":"2024-06-27","paper":"/paper/robouniview-visual-language-model-with","paper_url":"https://arxiv.org/abs/2406.18977v3","paper_title":"RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation","code":"https://github.com/liufanfanlff/robouniview","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"UniVLA","metrics":{"avg. sequence length (D to D)":"3.80"},"uses_additional_data":false,"paper_date":"2025-05-09","paper":"/paper/univla-learning-to-act-anywhere-with-task","paper_url":"https://arxiv.org/abs/2505.06111v2","paper_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","code":"https://github.com/opendrivelab/univla","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"RoboDual","metrics":{"avg. sequence length (D to D)":"3.66"},"uses_additional_data":false,"paper_date":"2024-10-10","paper":"/paper/towards-synergistic-generalized-and-efficient","paper_url":"https://arxiv.org/abs/2410.08001v3","paper_title":"Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"VidMan","metrics":{"avg. sequence length (D to D)":"3.42"},"uses_additional_data":false,"paper_date":"2024-11-14","paper":"/paper/vidman-exploiting-implicit-dynamics-from","paper_url":"https://arxiv.org/abs/2411.09153v1","paper_title":"VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"3DDA","metrics":{"avg. sequence length (D to D)":"3.35"},"uses_additional_data":false,"paper_date":"2024-02-18","paper":"/paper/3d-diffuser-actor-policy-diffusion-with-3d","paper_url":"https://arxiv.org/abs/2402.10885","paper_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","code":"https://github.com/nickgkan/3d_diffuser_actor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"OpenVLA","metrics":{"avg. sequence length (D to D)":"3.27"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/openvla-an-open-source-vision-language-action","paper_url":"https://arxiv.org/abs/2406.09246v3","paper_title":"OpenVLA: An Open-Source Vision-Language-Action Model","code":"https://github.com/openvla/openvla","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"3D Diffusor Actor","metrics":{"avg. sequence length (D to D)":"3.27"},"uses_additional_data":false,"paper_date":"2024-02-18","paper":"/paper/3d-diffuser-actor-policy-diffusion-with-3d","paper_url":"https://arxiv.org/abs/2402.10885","paper_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","code":"https://github.com/nickgkan/3d_diffuser_actor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"GR-1","metrics":{"avg. sequence length (D to D)":"3.06"},"uses_additional_data":false,"paper_date":"2023-12-20","paper":"/paper/unleashing-large-scale-video-generative-pre","paper_url":"https://arxiv.org/abs/2312.13139v2","paper_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","code":"https://github.com/bytedance/gr-1","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"Roboflamingo","metrics":{"avg. sequence length (D to D)":"2.47"},"uses_additional_data":false,"paper_date":"2023-11-02","paper":"/paper/vision-language-foundation-models-as","paper_url":"https://arxiv.org/abs/2311.01378v3","paper_title":"Vision-Language Foundation Models as Effective Robot Imitators","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"LCB","metrics":{"avg. sequence length (D to D)":"1.78"},"uses_additional_data":false,"paper_date":"2024-05-08","paper":"/paper/from-llms-to-actions-latent-codes-as-bridges","paper_url":"https://arxiv.org/abs/2405.04798v2","paper_title":"From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"Uni-Pi","metrics":{"avg. sequence length (D to D)":"0.92"},"uses_additional_data":false,"paper_date":"2023-01-31","paper":"/paper/learning-universal-policies-via-text-guided","paper_url":"https://arxiv.org/abs/2302.00111v3","paper_title":"Learning Universal Policies via Text-Guided Video Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"RT-1","metrics":{"avg. sequence length (D to D)":"0.90"},"uses_additional_data":false,"paper_date":"2022-12-13","paper":"/paper/rt-1-robotics-transformer-for-real-world","paper_url":"https://arxiv.org/abs/2212.06817v2","paper_title":"RT-1: Robotics Transformer for Real-World Control at Scale","code":"https://github.com/google-research/robotics_transformer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}}],"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":13,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":12,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":24,"n_unverified":55,"n_samples":79,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":24,"n_unverified":64,"n_samples":88,"n_pointer_only_licence":4,"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"}}}