{"url":"/sota/mmr-total-on-mrr-benchmark","task":{"name":"MMR total","url":"/task/mmr-total","note":null},"dataset":{"name":"MRR-Benchmark","url":"/dataset/mrr-benchmark"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Sum of all scores of the 11 distinct tasks involving texts, fonts, visual elements, bounding boxes, spatial relations, and grounding in the Multi-Modal Reading (MMR) Benchmark.","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":["Total Column Score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Total Column Score":"higher"}},"counts":{"rows":14,"rows_with_code":10,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":14},"rows":[{"rank_in_archive_order":1,"model":"Claude 3.5 Sonnet","metrics":{"Total Column Score":"463"},"uses_additional_data":true,"paper_date":"2024-06-24","paper":"/paper/claude-3-5-sonnet-model-card-addendum","paper_url":"https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf","paper_title":"Claude 3.5 Sonnet Model Card Addendum","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"GPT-4o","metrics":{"Total Column Score":"457"},"uses_additional_data":true,"paper_date":"2024-06-14","paper":"/paper/gpt-4o-visual-perception-performance-of","paper_url":"https://arxiv.org/abs/2406.09781v1","paper_title":"GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"GPT-4V","metrics":{"Total Column Score":"415"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/the-dawn-of-lmms-preliminary-explorations","paper_url":"https://arxiv.org/abs/2309.17421v2","paper_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","code":"https://github.com/qi-zhangyang/gemini-vs-gpt4v","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"LLaVA-NEXT-34B","metrics":{"Total Column Score":"412"},"uses_additional_data":true,"paper_date":"2023-04-17","paper":"/paper/visual-instruction-tuning-1","paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","code":"https://github.com/huggingface/transformers","n_code_links":13,"syntology":{"n_ran":16,"n_unverified":35,"n_samples":51,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Phi-3-Vision","metrics":{"Total Column Score":"397"},"uses_additional_data":true,"paper_date":"2024-04-22","paper":"/paper/phi-3-technical-report-a-highly-capable","paper_url":"https://arxiv.org/abs/2404.14219v4","paper_title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"InternVL2-8B","metrics":{"Total Column Score":"368"},"uses_additional_data":true,"paper_date":"2023-12-21","paper":"/paper/internvl-scaling-up-vision-foundation-models","paper_url":"https://arxiv.org/abs/2312.14238v3","paper_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","code":"https://github.com/opengvlab/internvl","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"Qwen-vl-max","metrics":{"Total Column Score":"366"},"uses_additional_data":true,"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}},{"rank_in_archive_order":8,"model":"LLaVA-NEXT-13B","metrics":{"Total Column Score":"335"},"uses_additional_data":true,"paper_date":"2023-04-17","paper":"/paper/visual-instruction-tuning-1","paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","code":"https://github.com/huggingface/transformers","n_code_links":13,"syntology":{"n_ran":16,"n_unverified":35,"n_samples":51,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"Qwen-vl-plus","metrics":{"Total Column Score":"310"},"uses_additional_data":true,"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}},{"rank_in_archive_order":10,"model":"Idefics-2-8B","metrics":{"Total Column Score":"256"},"uses_additional_data":true,"paper_date":"2024-05-03","paper":"/paper/what-matters-when-building-vision-language","paper_url":"https://arxiv.org/abs/2405.02246v1","paper_title":"What matters when building vision-language models?","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"LLaVA-1.5-13B","metrics":{"Total Column Score":"243"},"uses_additional_data":true,"paper_date":"2023-04-17","paper":"/paper/visual-instruction-tuning-1","paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","code":"https://github.com/huggingface/transformers","n_code_links":13,"syntology":{"n_ran":16,"n_unverified":35,"n_samples":51,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"InternVL2-1B","metrics":{"Total Column Score":"237"},"uses_additional_data":true,"paper_date":"2023-12-21","paper":"/paper/internvl-scaling-up-vision-foundation-models","paper_url":"https://arxiv.org/abs/2312.14238v3","paper_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","code":"https://github.com/opengvlab/internvl","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"Monkey-Chat-7B","metrics":{"Total Column Score":"214"},"uses_additional_data":true,"paper_date":"2023-11-11","paper":"/paper/monkey-image-resolution-and-text-label-are","paper_url":"https://arxiv.org/abs/2311.06607v4","paper_title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","code":"https://github.com/yuliang-liu/monkey","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Idefics-80B","metrics":{"Total Column Score":"139"},"uses_additional_data":true,"paper_date":"2023-06-21","paper":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1","paper_url":"https://arxiv.org/abs/2306.16527v2","paper_title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","code":"https://github.com/huggingface/obelics","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"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":9,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":38,"n_samples":57,"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":53,"n_unverified":110,"n_samples":163,"n_pointer_only_licence":8,"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"}}}