{"url":"/sota/natural-language-visual-grounding-on","task":{"name":"Natural Language Visual Grounding","url":"/task/natural-language-visual-grounding","note":null},"dataset":{"name":"ScreenSpot","url":"/dataset/screenspot"},"category":"Reasoning","categories":["Reasoning"],"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":["Accuracy (%)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (%)":"higher"}},"counts":{"rows":18,"rows_with_code":18,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"UGround-V1-7B","metrics":{"Accuracy (%)":"86.34"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/navigating-the-digital-world-as-humans-do","paper_url":"https://arxiv.org/abs/2410.05243v1","paper_title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","code":"https://github.com/OSU-NLP-Group/UGround","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Aguvis-7B","metrics":{"Accuracy (%)":"83.0"},"uses_additional_data":false,"paper_date":"2024-12-05","paper":"/paper/aguvis-unified-pure-vision-agents-for","paper_url":"https://arxiv.org/abs/2412.04454v2","paper_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","code":"https://github.com/xlang-ai/aguvis","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"OS-Atlas-Base-7B","metrics":{"Accuracy (%)":"82.47"},"uses_additional_data":false,"paper_date":"2024-10-30","paper":"/paper/os-atlas-a-foundation-action-model-for","paper_url":"https://arxiv.org/abs/2410.23218v1","paper_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","code":"https://github.com/njucckevin/seeclick","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Aria-UI","metrics":{"Accuracy (%)":"81.1"},"uses_additional_data":false,"paper_date":"2024-12-20","paper":"/paper/aria-ui-visual-grounding-for-gui-instructions","paper_url":"https://arxiv.org/abs/2412.16256v1","paper_title":"Aria-UI: Visual Grounding for GUI Instructions","code":"https://github.com/ariaui/aria-ui","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"Aguvis-G-7B","metrics":{"Accuracy (%)":"81.0"},"uses_additional_data":false,"paper_date":"2024-12-05","paper":"/paper/aguvis-unified-pure-vision-agents-for","paper_url":"https://arxiv.org/abs/2412.04454v2","paper_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","code":"https://github.com/xlang-ai/aguvis","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"UGround-V1-2B","metrics":{"Accuracy (%)":"77.67"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/navigating-the-digital-world-as-humans-do","paper_url":"https://arxiv.org/abs/2410.05243v1","paper_title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","code":"https://github.com/OSU-NLP-Group/UGround","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ShowUI","metrics":{"Accuracy (%)":"75.1"},"uses_additional_data":false,"paper_date":"2024-11-26","paper":"/paper/showui-one-vision-language-action-model-for","paper_url":"https://arxiv.org/abs/2411.17465v1","paper_title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","code":"https://github.com/showlab/showui","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":15,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"ShowUI-G","metrics":{"Accuracy (%)":"75.0"},"uses_additional_data":false,"paper_date":"2024-11-26","paper":"/paper/showui-one-vision-language-action-model-for","paper_url":"https://arxiv.org/abs/2411.17465v1","paper_title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","code":"https://github.com/showlab/showui","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":15,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"UGround","metrics":{"Accuracy (%)":"73.3"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/navigating-the-digital-world-as-humans-do","paper_url":"https://arxiv.org/abs/2410.05243v1","paper_title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","code":"https://github.com/OSU-NLP-Group/UGround","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"OmniParser","metrics":{"Accuracy (%)":"73.0"},"uses_additional_data":false,"paper_date":"2024-08-01","paper":"/paper/omniparser-for-pure-vision-based-gui-agent","paper_url":"https://arxiv.org/abs/2408.00203v1","paper_title":"OmniParser for Pure Vision Based GUI Agent","code":"https://github.com/microsoft/omniparser","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"OS-Atlas-Base-4B","metrics":{"Accuracy (%)":"68.0"},"uses_additional_data":false,"paper_date":"2024-10-30","paper":"/paper/os-atlas-a-foundation-action-model-for","paper_url":"https://arxiv.org/abs/2410.23218v1","paper_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","code":"https://github.com/njucckevin/seeclick","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SeeClick","metrics":{"Accuracy (%)":"53.4"},"uses_additional_data":false,"paper_date":"2024-01-17","paper":"/paper/seeclick-harnessing-gui-grounding-for","paper_url":"https://arxiv.org/abs/2401.10935v2","paper_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","code":"https://github.com/njucckevin/seeclick","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"CogAgent","metrics":{"Accuracy (%)":"47.4"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/cogagent-a-visual-language-model-for-gui","paper_url":"https://arxiv.org/abs/2312.08914v3","paper_title":"CogAgent: A Visual Language Model for GUI Agents","code":"https://github.com/thudm/cogvlm","n_code_links":3,"syntology":{"n_ran":12,"n_unverified":6,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Qwen2-VL-7B","metrics":{"Accuracy (%)":"42.1"},"uses_additional_data":false,"paper_date":"2024-09-18","paper":"/paper/qwen2-vl-enhancing-vision-language-model-s","paper_url":"https://arxiv.org/abs/2409.12191v2","paper_title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","code":"https://github.com/qwenlm/qwen2-vl","n_code_links":8,"syntology":{"n_ran":12,"n_unverified":0,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"Qwen-GUI","metrics":{"Accuracy (%)":"28.6"},"uses_additional_data":false,"paper_date":"2024-06-17","paper":"/paper/guicourse-from-general-vision-language-models","paper_url":"https://arxiv.org/abs/2406.11317v2","paper_title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","code":"https://github.com/yiye3/guicourse","n_code_links":1,"syntology":{"n_ran":15,"n_unverified":1,"n_samples":16,"n_pointer_only_licence":16}},{"rank_in_archive_order":16,"model":"MiniGPT-v2","metrics":{"Accuracy (%)":"5.7"},"uses_additional_data":false,"paper_date":"2023-10-14","paper":"/paper/minigpt-v2-large-language-model-as-a-unified","paper_url":"https://arxiv.org/abs/2310.09478v3","paper_title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","code":"https://github.com/vision-cair/minigpt-4","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"Groma","metrics":{"Accuracy (%)":"5.2"},"uses_additional_data":false,"paper_date":"2024-04-19","paper":"/paper/groma-localized-visual-tokenization-for","paper_url":"https://arxiv.org/abs/2404.13013v1","paper_title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","code":"https://github.com/FoundationVision/Groma","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Qwen-VL","metrics":{"Accuracy (%)":"5.2"},"uses_additional_data":false,"paper_date":"2023-08-24","paper":"/paper/qwen-vl-a-frontier-large-vision-language","paper_url":"https://arxiv.org/abs/2308.12966v3","paper_title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","code":"https://github.com/qwenlm/qwen-vl","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":15,"rows_with_any_sample_ran":11,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":52,"n_unverified":29,"n_samples":81,"n_pointer_only_licence":21,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":54,"n_unverified":46,"n_samples":100,"n_pointer_only_licence":21,"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"}}}