{"url":"/dataset/mrr-benchmark","name":"MRR-Benchmark","full_name":"Multi-Modal Reading Benchmark","description_markdown":"Multi-Modal Reading (MMR) Benchmark includes 550 annotated question-answer pairs across 11 distinct tasks involving texts, fonts, visual elements, bounding boxes, spatial relations, and grounding, with carefully designed evaluation metrics.","description_withheld":null,"homepage":"https://huggingface.co/datasets/puar-playground/MMR","introduced_date":"2024-08-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/mmr-evaluating-reading-ability-of-large","title":"MMR: Evaluating Reading Ability of Large Multimodal Models","first_author":"Jian Chen","url":null},"license":{"name":"Apache License","url":"https://www.apache.org/licenses/LICENSE-2.0"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Font Recognition","url":"/task/font-recognition","datasets_with_task":"/datasets/task/font-recognition"},{"name":"Visual Grounding","url":"/task/visual-grounding","datasets_with_task":"/datasets/task/visual-grounding"},{"name":"Spatial Relation Recognition","url":"/task/spatial-relation-recognition","datasets_with_task":"/datasets/task/spatial-relation-recognition"},{"name":"MMR total","url":"/task/mmr-total","datasets_with_task":"/datasets/task/mmr-total"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MRR-Benchmark"],"data_loaders":[{"repo":"https://github.com/llavar/MMR_Bench","url":"https://llavar.github.io/mmr/","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset_variant":"MRR-Benchmark","rows":14,"metrics":["Total Column Score"],"first_row_in_archive_order":{"model":"Claude 3.5 Sonnet","paper":"/paper/claude-3-5-sonnet-model-card-addendum","metrics":{"Total Column Score":"463"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/claude-3-5-sonnet-model-card-addendum","title":"Claude 3.5 Sonnet Model Card Addendum","date":"2024-06-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gpt-4o-visual-perception-performance-of","title":"GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding","date":"2024-06-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/what-matters-when-building-vision-language","title":"What matters when building vision-language models?","date":"2024-05-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phi-3-technical-report-a-highly-capable","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","date":"2024-04-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-dawn-of-lmms-preliminary-explorations","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","date":"2023-09-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","rows_on_this_dataset":3,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":51,"samples_ran":16,"samples_unverified":35,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":57,"samples_ran":19,"samples_unverified":38,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}