{"url":"/sota/open-domain-question-answering-on-searchqa","task":{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","note":null},"dataset":{"name":"SearchQA","url":"/dataset/searchqa"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Open-domain question answering is the task of question answering on open-domain datasets such as Wikipedia.","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":["EM","N-gram F1","Unigram Acc","F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"EM":null,"N-gram F1":"higher","Unigram Acc":"higher","F1":"higher"}},"counts":{"rows":14,"rows_with_code":10,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Cluster-Former (#C=512)","metrics":{"EM":"68.0"},"uses_additional_data":false,"paper_date":"2020-09-13","paper":"/paper/cluster-former-clustering-based-sparse","paper_url":"https://arxiv.org/abs/2009.06097v2","paper_title":"Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Locality-Sensitive Hashing","metrics":{"EM":"66.0"},"uses_additional_data":false,"paper_date":"2020-01-13","paper":"/paper/reformer-the-efficient-transformer-1","paper_url":"https://arxiv.org/abs/2001.04451v2","paper_title":"Reformer: The Efficient Transformer","code":"https://github.com/huggingface/transformers","n_code_links":10,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Multi-passage BERT","metrics":{"EM":"65.1"},"uses_additional_data":false,"paper_date":"2019-08-22","paper":"/paper/multi-passage-bert-a-globally-normalized-bert","paper_url":"https://arxiv.org/abs/1908.08167v2","paper_title":"Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Sparse Attention","metrics":{"EM":"64.7"},"uses_additional_data":false,"paper_date":"2019-04-23","paper":"/paper/190410509","paper_url":"http://arxiv.org/abs/1904.10509v1","paper_title":"Generating Long Sequences with Sparse Transformers","code":"https://github.com/mistralai/mistral-src","n_code_links":7,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"DECAPROP","metrics":{"EM":"62.2"},"uses_additional_data":false,"paper_date":"2018-11-10","paper":"/paper/densely-connected-attention-propagation-for","paper_url":"http://arxiv.org/abs/1811.04210v2","paper_title":"Densely Connected Attention Propagation for Reading Comprehension","code":"https://github.com/vanzytay/NIPS2018_DECAPROP","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Denoising QA","metrics":{"EM":"58.8","F1":"64.5","N-gram F1":"-","Unigram Acc":"-"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/denoising-distantly-supervised-open-domain","paper_url":"https://aclanthology.org/P18-1161","paper_title":"Denoising Distantly Supervised Open-Domain Question Answering","code":"https://github.com/thunlp/OpenQA","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DecaProp","metrics":{"EM":"56.8","F1":"63.6","N-gram F1":"70.8","Unigram Acc":"62.2"},"uses_additional_data":false,"paper_date":"2018-11-10","paper":"/paper/densely-connected-attention-propagation-for","paper_url":"http://arxiv.org/abs/1811.04210v2","paper_title":"Densely Connected Attention Propagation for Reading Comprehension","code":"https://github.com/vanzytay/NIPS2018_DECAPROP","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"R^3","metrics":{"EM":"49.0","F1":"55.3","N-gram F1":"-","Unigram Acc":"-"},"uses_additional_data":false,"paper_date":"2017-08-31","paper":"/paper/r3-reinforced-reader-ranker-for-open-domain","paper_url":"http://arxiv.org/abs/1709.00023v2","paper_title":"R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering","code":"https://github.com/shuohangwang/mprc","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"DrQA","metrics":{"EM":"41.9"},"uses_additional_data":false,"paper_date":"2017-03-31","paper":"/paper/reading-wikipedia-to-answer-open-domain","paper_url":"http://arxiv.org/abs/1704.00051v2","paper_title":"Reading Wikipedia to Answer Open-Domain Questions","code":"https://github.com/facebookresearch/ParlAI","n_code_links":10,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"Bi-Attention + DCU-LSTM","metrics":{"EM":"-","F1":"-","N-gram F1":"59.5","Unigram Acc":"49.4"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/multi-granular-sequence-encoding-via-dilated","paper_url":"https://aclanthology.org/D18-1238","paper_title":"Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"AMANDA","metrics":{"EM":"-","F1":"-","N-gram F1":"56.6","Unigram Acc":"46.8"},"uses_additional_data":false,"paper_date":"2018-01-25","paper":"/paper/a-question-focused-multi-factor-attention","paper_url":"http://arxiv.org/abs/1801.08290v1","paper_title":"A Question-Focused Multi-Factor Attention Network for Question Answering","code":"https://github.com/nusnlp/amanda","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Focused Hierarchical RNN","metrics":{"N-gram F1":"53.4","Unigram Acc":"46.8"},"uses_additional_data":false,"paper_date":"2018-06-12","paper":"/paper/focused-hierarchical-rnns-for-conditional","paper_url":"http://arxiv.org/abs/1806.04342v1","paper_title":"Focused Hierarchical RNNs for Conditional Sequence Processing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"ASR","metrics":{"N-gram F1":"22.8","Unigram Acc":"41.3"},"uses_additional_data":false,"paper_date":"2016-03-04","paper":"/paper/text-understanding-with-the-attention-sum","paper_url":"http://arxiv.org/abs/1603.01547v2","paper_title":"Text Understanding with the Attention Sum Reader Network","code":"https://github.com/rkadlec/asreader","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"SpanBERT","metrics":{"F1":"84.8"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/spanbert-improving-pre-training-by","paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","code":"https://github.com/facebookresearch/SpanBERT","n_code_links":6,"syntology":{"n_ran":6,"n_unverified":9,"n_samples":15,"n_pointer_only_licence":4}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":18,"n_unverified":22,"n_samples":40,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":18,"n_unverified":22,"n_samples":40,"n_pointer_only_licence":5,"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"}}}