{"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/drop","name":"DROP","full_name":"Discrete Reasoning Over Paragraphs","description_markdown":"**Discrete Reasoning Over Paragraphs** **DROP** is a crowdsourced, adversarially-created, 96k-question benchmark, in which a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as addition, counting, or sorting). These operations require a much more comprehensive understanding of the content of paragraphs than what was necessary for prior datasets. The questions consist of passages extracted from Wikipedia articles. The dataset is split into a training set of about 77,000 questions, a development set of around 9,500 questions and a hidden test set similar in size to the development set.\r\n\r\nSource: [https://allennlp.org/drop](https://allennlp.org/drop)\r\nImage Source: [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://paperswithcode.com/paper/drop-a-reading-comprehension-benchmark/)","description_withheld":null,"homepage":"https://allennlp.org/drop","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/drop-a-reading-comprehension-benchmark","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","first_author":"Dheeru Dua","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DROP Test","DROP","Drop (3-Shot)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/drop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/swap-uniba/drop_ita","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ucinlp/drop","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/drop","frameworks":["tf","jax"]},{"repo":"https://github.com/RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox/blob/main/docs/utilization/supported-datasets.md","frameworks":["pytorch"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/rc/dataset_readers/drop/","frameworks":["pytorch"]}],"num_papers_in_archive":382,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-drop-test","task":"Question Answering","dataset_variant":"DROP Test","rows":16,"metrics":["F1"],"first_row_in_archive_order":{"model":"QDGAT (ensemble)","paper":"/paper/question-directed-graph-attention-network-for","metrics":{"F1":"88.38"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-drop","task":"Question Answering","dataset_variant":"DROP","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 540B (Self Improvement, Self Consistency)","paper":"/paper/large-language-models-can-self-improve","metrics":{"Accuracy":"83"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-drop-3-shot","task":"Text Generation","dataset_variant":"Drop (3-Shot)","rows":0,"metrics":["f1 score"],"first_row_in_archive_order":null,"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":14,"of":14,"counts":{"papers_with_a_benchmark_row":14,"with_a_code_link":9,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/orca-2-teaching-small-language-models-how-to","slug":"orca-2-teaching-small-language-models-how-to","title":"Orca 2: Teaching Small Language Models How to Reason","date":"2023-11-18","arxiv_id":"2311.11045","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"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/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/reasoning-like-program-executors-1","slug":"reasoning-like-program-executors-1","title":"Reasoning Like Program Executors","date":"2022-01-27","arxiv_id":"2201.11473","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/question-directed-graph-attention-network-for","slug":"question-directed-graph-attention-network-for","title":"Question Directed Graph Attention Network for Numerical Reasoning over Text","date":"2020-09-16","arxiv_id":"2009.07448","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/neural-symbolic-reader-scalable-integration","slug":"neural-symbolic-reader-scalable-integration","title":"Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension","date":"2020-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/injecting-numerical-reasoning-skills-into","slug":"injecting-numerical-reasoning-skills-into","title":"Injecting Numerical Reasoning Skills into Language Models","date":"2020-04-09","arxiv_id":"2004.04487","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/numnet-machine-reading-comprehension-with","slug":"numnet-machine-reading-comprehension-with","title":"NumNet: Machine Reading Comprehension with Numerical Reasoning","date":"2019-10-15","arxiv_id":"1910.06701","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tag-based-multi-span-extraction-in-reading","slug":"tag-based-multi-span-extraction-in-reading","title":"A Simple and Effective Model for Answering Multi-span Questions","date":"2019-09-29","arxiv_id":"1909.13375","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/giving-bert-a-calculator-finding-operations","slug":"giving-bert-a-calculator-finding-operations","title":"Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension","date":"2019-08-31","arxiv_id":"1909.00109","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-multi-type-multi-span-network-for-reading","slug":"a-multi-type-multi-span-network-for-reading","title":"A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning","date":"2019-08-15","arxiv_id":"1908.05514","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/drop-a-reading-comprehension-benchmark","slug":"drop-a-reading-comprehension-benchmark","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","date":"2019-03-01","arxiv_id":"1903.00161","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/orca-2-teaching-small-language-models-how-to","slug":"orca-2-teaching-small-language-models-how-to","title":"Orca 2: Teaching Small Language Models How to Reason","date":"2023-11-18","arxiv_id":"2311.11045","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"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/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/reasoning-like-program-executors-1","slug":"reasoning-like-program-executors-1","title":"Reasoning Like Program Executors","date":"2022-01-27","arxiv_id":"2201.11473","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/question-directed-graph-attention-network-for","slug":"question-directed-graph-attention-network-for","title":"Question Directed Graph Attention Network for Numerical Reasoning over Text","date":"2020-09-16","arxiv_id":"2009.07448","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/neural-symbolic-reader-scalable-integration","slug":"neural-symbolic-reader-scalable-integration","title":"Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension","date":"2020-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/injecting-numerical-reasoning-skills-into","slug":"injecting-numerical-reasoning-skills-into","title":"Injecting Numerical Reasoning Skills into Language Models","date":"2020-04-09","arxiv_id":"2004.04487","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/numnet-machine-reading-comprehension-with","slug":"numnet-machine-reading-comprehension-with","title":"NumNet: Machine Reading Comprehension with Numerical Reasoning","date":"2019-10-15","arxiv_id":"1910.06701","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tag-based-multi-span-extraction-in-reading","slug":"tag-based-multi-span-extraction-in-reading","title":"A Simple and Effective Model for Answering Multi-span Questions","date":"2019-09-29","arxiv_id":"1909.13375","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/giving-bert-a-calculator-finding-operations","slug":"giving-bert-a-calculator-finding-operations","title":"Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension","date":"2019-08-31","arxiv_id":"1909.00109","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-multi-type-multi-span-network-for-reading","slug":"a-multi-type-multi-span-network-for-reading","title":"A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning","date":"2019-08-15","arxiv_id":"1908.05514","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/drop-a-reading-comprehension-benchmark","slug":"drop-a-reading-comprehension-benchmark","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","date":"2019-03-01","arxiv_id":"1903.00161","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/drop/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/drop/papers/ran/1","json":"/dataset/drop/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":70,"samples_ran":50,"samples_constructed":0,"samples_ran_checked":42,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"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":"75731c73231cbf4064ac2bea8921816413c80cba13706a1254c0f2b341e5c360","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}