{"url":"/sota/reading-comprehension-on-reclor","task":{"name":"Reading Comprehension","url":"/task/reading-comprehension","note":null},"dataset":{"name":"ReClor","url":"/dataset/reclor"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph or document and the answer often is a span in the document. \r\n\r\nSome specific tasks of reading comprehension include multi-modal machine reading comprehension and textual machine reading comprehension, among others. In the literature, machine reading comprehension can be divide into four categories: **cloze style**, **multiple choice**, **span prediction**, and **free-form answer**.  Read more about each category [here](https://paperswithcode.com/paper/a-survey-on-machine-reading-comprehension-1).\r\n\r\nBenchmark datasets used for testing a model's reading comprehension abilities include [MovieQA](/dataset/movieqa), [ReCoRD](dataset/record), and [RACE](/dataset/race), among others.\r\n\r\nThe Machine Reading group at UCL also provides an [overview of reading comprehension tasks](https://uclnlp.github.io/ai4exams/data.html).\r\n\r\nFigure source: [A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets](https://arxiv.org/pdf/2006.11880.pdf)","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":["Test"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test":null}},"counts":{"rows":39,"rows_with_code":10,"rows_with_paper_page":11,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Rational Reasoner / IDOL","metrics":{"Test":"80.6"},"uses_additional_data":false,"paper_date":"2023-06-27","paper":"/paper/idol-indicator-oriented-logic-pre-training","paper_url":"https://arxiv.org/abs/2306.15273v1","paper_title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","code":"https://github.com/GeekDream-x/IDOL","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"AMR-LE-Ensemble","metrics":{"Test":"80.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"MERIt(MERIt-deberta-v2-xxlarge )","metrics":{"Test":"79.3"},"uses_additional_data":false,"paper_date":"2022-03-01","paper":"/paper/merit-meta-path-guided-contrastive-learning","paper_url":"https://arxiv.org/abs/2203.00357v1","paper_title":"MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning","code":"https://github.com/sparkjiao/merit","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MERIt-deberta-v2-xxlarge       deberta.v2.xxlarge.path.override_True.norm_1.1.0.w2.A100.cp200.s42","metrics":{"Test":"79.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Knowledge model","metrics":{"Test":"79.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"DeBERTa-v2-xxlarge-AMR-LE-Contraposition","metrics":{"Test":"77.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"LReasoner ensemble","metrics":{"Test":"76.1"},"uses_additional_data":false,"paper_date":"2021-05-08","paper":"/paper/logic-driven-context-extension-and-data","paper_url":"https://arxiv.org/abs/2105.03659v1","paper_title":"Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text","code":"https://github.com/WangsyGit/LReasoner","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"ELECTRA and ALBERT","metrics":{"Test":"71.0"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/answer-uncertainty-and-unanswerability-in-1","paper_url":"https://aclanthology.org/2022.findings-acl.82","paper_title":"Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading Comprehension","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"WWZ","metrics":{"Test":"69.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"xlnet-large-uncased [extended data]","metrics":{"Test":"69.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"albert_4gpus_bs2_DACE","metrics":{"Test":"68.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Tournament2","metrics":{"Test":"66.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"MERIt + Structure Decouple (roberta-large)","metrics":{"Test":"65.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"RoBERTa-single","metrics":{"Test":"63.5"},"uses_additional_data":false,"paper_date":"2022-05-02","paper":"/paper/logiformer-a-two-branch-graph-transformer","paper_url":"https://arxiv.org/abs/2205.00731v2","paper_title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","code":"https://github.com/xufangzhi/logiformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"MERIT w/ reasoning aware","metrics":{"Test":"63.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ALBERT-XXLarge-V2","metrics":{"Test":"62.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"VDGN(RoBERTa single model)","metrics":{"Test":"61.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"ro_DA_CE_v100_224","metrics":{"Test":"61.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"qmcurtis","metrics":{"Test":"60.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"AdaLoGN","metrics":{"Test":"60.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"Zhangjie666","metrics":{"Test":"60.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"alsace","metrics":{"Test":"59.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"RoBERTa-single","metrics":{"Test":"58.9"},"uses_additional_data":false,"paper_date":"2021-05-21","paper":"/paper/fact-driven-logical-reasoning","paper_url":"https://arxiv.org/abs/2105.10334v2","paper_title":"Fact-driven Logical Reasoning for Machine Reading Comprehension","code":"https://github.com/ozyyshr/DGM","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"NAACL 2021","metrics":{"Test":"58.2"},"uses_additional_data":false,"paper_date":"2021-03-26","paper":"/paper/dagn-discourse-aware-graph-network-for","paper_url":"https://arxiv.org/abs/2103.14349v2","paper_title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","code":"https://github.com/xufangzhi/logiformer","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":25,"model":"Roberta Large GCN(dev: 0.63)","metrics":{"Test":"57.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"xlnet_l","metrics":{"Test":"57.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"elBERto","metrics":{"Test":"57.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"5BitClan","metrics":{"Test":"56.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"SimChea","metrics":{"Test":"56.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"XLNet-large","metrics":{"Test":"56.0"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/reclor-a-reading-comprehension-dataset-1","paper_url":"https://arxiv.org/abs/2002.04326v3","paper_title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","code":"https://github.com/yuweihao/reclor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":31,"model":"RoBERTa-large","metrics":{"Test":"55.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"XLNet-base","metrics":{"Test":"50.4"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/reclor-a-reading-comprehension-dataset-1","paper_url":"https://arxiv.org/abs/2002.04326v3","paper_title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","code":"https://github.com/yuweihao/reclor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":33,"model":"BERT-large+MNLI","metrics":{"Test":"50.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"BERT-large","metrics":{"Test":"49.8"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"RoBERTa-base","metrics":{"Test":"48.5"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/reclor-a-reading-comprehension-dataset-1","paper_url":"https://arxiv.org/abs/2002.04326v3","paper_title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","code":"https://github.com/yuweihao/reclor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":36,"model":"BERT-base","metrics":{"Test":"47.3"},"uses_additional_data":false,"paper_date":"2020-02-11","paper":"/paper/reclor-a-reading-comprehension-dataset-1","paper_url":"https://arxiv.org/abs/2002.04326v3","paper_title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","code":"https://github.com/yuweihao/reclor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":37,"model":"Gariscat","metrics":{"Test":"40.5"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"BachTE","metrics":{"Test":"26.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"TwistedFate","metrics":{"Test":"25.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null}],"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":6,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":13,"n_samples":20,"n_pointer_only_licence":13,"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"}}}