{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":6,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/claude-3-5-sonnet-model-card-addendum","slug":"claude-3-5-sonnet-model-card-addendum","title":"Claude 3.5 Sonnet Model Card Addendum","date":"2024-06-24","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gpt-4o-visual-perception-performance-of","slug":"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","arxiv_id":"2406.09781","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/what-matters-when-building-vision-language","slug":"what-matters-when-building-vision-language","title":"What matters when building vision-language models?","date":"2024-05-03","arxiv_id":"2405.02246","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phi-3-technical-report-a-highly-capable","slug":"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","arxiv_id":"2404.14219","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvl-scaling-up-vision-foundation-models","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}}}},{"paper":"/paper/monkey-image-resolution-and-text-label-are","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monkey-image-resolution-and-text-label-are#ran","syntology_url":"https://syntology.ai/paper/2311.06607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06607"}}}},{"paper":"/paper/the-dawn-of-lmms-preliminary-explorations","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}}}},{"paper":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["huggingface/obelics"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1#ran","syntology_url":"https://syntology.ai/paper/2306.16527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16527"}}}},{"paper":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","rows_on_this_dataset":3,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":51,"samples_ran":16,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":8,"samples_unverified":35,"pointer_only_for_licence":0,"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/claude-3-5-sonnet-model-card-addendum","slug":"claude-3-5-sonnet-model-card-addendum","title":"Claude 3.5 Sonnet Model Card Addendum","date":"2024-06-24","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gpt-4o-visual-perception-performance-of","slug":"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","arxiv_id":"2406.09781","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/what-matters-when-building-vision-language","slug":"what-matters-when-building-vision-language","title":"What matters when building vision-language models?","date":"2024-05-03","arxiv_id":"2405.02246","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/phi-3-technical-report-a-highly-capable","slug":"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","arxiv_id":"2404.14219","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvl-scaling-up-vision-foundation-models","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}}}},{"paper":"/paper/monkey-image-resolution-and-text-label-are","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/monkey-image-resolution-and-text-label-are#ran","syntology_url":"https://syntology.ai/paper/2311.06607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06607"}}}},{"paper":"/paper/the-dawn-of-lmms-preliminary-explorations","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}}}},{"paper":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["huggingface/obelics"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/obelics-an-open-web-scale-filtered-dataset-of-1#ran","syntology_url":"https://syntology.ai/paper/2306.16527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16527"}}}},{"paper":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","rows_on_this_dataset":3,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":51,"samples_ran":16,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":8,"samples_unverified":35,"pointer_only_for_licence":0,"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/mrr-benchmark/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/mrr-benchmark/papers/ran/1","json":"/dataset/mrr-benchmark/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":57,"samples_ran":19,"samples_constructed":8,"samples_ran_checked":10,"samples_ran_instrument_failed":9,"samples_unverified":38,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"20f2e5564fa57093c8545b0dfada8a97dfc8013cdd1fc463f80735e8eb1adb5f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}