{"url":"/task/mmr-total","name":"MMR total","slug":"mmr-total","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":12,"papers_with_code":7,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","slug":"mmr-total-on-mrr-benchmark","dataset":"MRR-Benchmark","dataset_url":"/dataset/mrr-benchmark","rows_in_archive":14,"metrics":["Total Column Score"],"first_row_in_archive_order":{"model":"Claude 3.5 Sonnet","paper_title":"Claude 3.5 Sonnet Model Card Addendum","paper_url":"/paper/claude-3-5-sonnet-model-card-addendum","paper_date":"2024-06-24","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/mrr-benchmark","name":"MRR-Benchmark","full_name":"Multi-Modal Reading Benchmark","num_papers_in_archive":11}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":12,"items":[{"url":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_unverified":35,"n_pointer_only":0}},{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/the-dawn-of-lmms-preliminary-explorations","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","date":"2023-09-29","arxiv_id":"2309.17421","repositories_listed":2,"syntology":null},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","arxiv_id":"2308.12966","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","date":"2023-06-21","arxiv_id":"2306.16527","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/monkey-image-resolution-and-text-label-are","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","date":"2023-11-11","arxiv_id":"2311.06607","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}