{"url":"/sota/text-classification-on-ag-news","task":{"name":"Text Classification","url":"/task/text-classification","note":null},"dataset":{"name":"AG News","url":"/dataset/ag-news"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Text Classification** is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics. \r\n\r\nText Classification problems include emotion classification, news classification, citation intent classification, among others. Benchmark datasets for evaluating text classification capabilities include GLUE, AGNews,  among others. \r\n\r\nIn recent years, deep learning techniques like XLNet and RoBERTa have attained some of the biggest performance jumps for text classification problems. \r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Text Classification Algorithms: A Survey](https://arxiv.org/pdf/1904.08067v4.pdf) )</span>","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":["Error"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Error":"lower"}},"counts":{"rows":24,"rows_with_code":22,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"XLNet","metrics":{"Error":"4.45"},"uses_additional_data":false,"paper_date":"2019-06-19","paper":"/paper/xlnet-generalized-autoregressive-pretraining","paper_url":"https://arxiv.org/abs/1906.08237v2","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":27,"syntology":{"n_ran":10,"n_unverified":14,"n_samples":24,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"BERT-ITPT-FiT","metrics":{"Error":"4.8"},"uses_additional_data":false,"paper_date":"2019-05-14","paper":"/paper/how-to-fine-tune-bert-for-text-classification","paper_url":"https://arxiv.org/abs/1905.05583v3","paper_title":"How to Fine-Tune BERT for Text Classification?","code":"https://github.com/xuyige/BERT4doc-Classification","n_code_links":15,"syntology":{"n_ran":6,"n_unverified":12,"n_samples":18,"n_pointer_only_licence":5}},{"rank_in_archive_order":3,"model":"L MIXED","metrics":{"Error":"4.95"},"uses_additional_data":false,"paper_date":"2020-09-08","paper":"/paper/revisiting-lstm-networks-for-semi-supervised-1","paper_url":"https://arxiv.org/abs/2009.04007v1","paper_title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","code":"https://github.com/DevSinghSachan/ssl_text_classification","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":4,"model":"ULMFiT","metrics":{"Error":"5.01"},"uses_additional_data":false,"paper_date":"2018-01-18","paper":"/paper/universal-language-model-fine-tuning-for-text","paper_url":"http://arxiv.org/abs/1801.06146v5","paper_title":"Universal Language Model Fine-tuning for Text Classification","code":"https://github.com/fastai/fastai","n_code_links":66,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"DRNN","metrics":{"Error":"5.53"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/disconnected-recurrent-neural-networks-for","paper_url":"https://aclanthology.org/P18-1215","paper_title":"Disconnected Recurrent Neural Networks for Text Categorization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"DNC+CUW","metrics":{"Error":"6.10"},"uses_additional_data":false,"paper_date":"2019-01-05","paper":"/paper/learning-to-remember-more-with-less","paper_url":"http://arxiv.org/abs/1901.01347v2","paper_title":"Learning to Remember More with Less Memorization","code":"https://github.com/thaihungle/UW-DNC","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ULMFiT (Small data)","metrics":{"Error":"6.3"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/sampling-bias-in-deep-active-classification","paper_url":"https://arxiv.org/abs/1909.09389v1","paper_title":"Sampling Bias in Deep Active Classification: An Empirical Study","code":"https://github.com/Xtra-Computing/thundersvm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"CNN","metrics":{"Error":"6.57"},"uses_additional_data":false,"paper_date":"2016-02-07","paper":"/paper/supervised-and-semi-supervised-text","paper_url":"http://arxiv.org/abs/1602.02373v2","paper_title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"DPCNN","metrics":{"Error":"6.87"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/deep-pyramid-convolutional-neural-networks","paper_url":"https://aclanthology.org/P17-1052","paper_title":"Deep Pyramid Convolutional Neural Networks for Text Categorization","code":"https://github.com/Cheneng/DPCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"EXAM","metrics":{"Error":"7"},"uses_additional_data":false,"paper_date":"2018-11-23","paper":"/paper/explicit-interaction-model-towards-text","paper_url":"http://arxiv.org/abs/1811.09386v1","paper_title":"Explicit Interaction Model towards Text Classification","code":"https://github.com/NonvolatileMemory/AAAI_2019_EXAM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"SWEM-concat","metrics":{"Error":"7.34"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/baseline-needs-more-love-on-simple-word","paper_url":"http://arxiv.org/abs/1805.09843v1","paper_title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","code":"https://github.com/dinghanshen/SWEM","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"Capsule-B","metrics":{"Error":"7.4"},"uses_additional_data":false,"paper_date":"2018-03-29","paper":"/paper/investigating-capsule-networks-with-dynamic","paper_url":"http://arxiv.org/abs/1804.00538v4","paper_title":"Investigating Capsule Networks with Dynamic Routing for Text Classification","code":"https://github.com/andyweizhao/capsule_text_classification","n_code_links":4,"syntology":null},{"rank_in_archive_order":13,"model":"fastText","metrics":{"Error":"7.5"},"uses_additional_data":false,"paper_date":"2016-07-06","paper":"/paper/bag-of-tricks-for-efficient-text","paper_url":"http://arxiv.org/abs/1607.01759v3","paper_title":"Bag of Tricks for Efficient Text Classification","code":"https://github.com/facebookresearch/fastText","n_code_links":65,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"LEAM","metrics":{"Error":"7.55"},"uses_additional_data":false,"paper_date":"2018-05-10","paper":"/paper/joint-embedding-of-words-and-labels-for-text","paper_url":"http://arxiv.org/abs/1805.04174v1","paper_title":"Joint Embedding of Words and Labels for Text Classification","code":"https://github.com/guoyinwang/LEAM","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"CCCapsNet","metrics":{"Error":"7.61"},"uses_additional_data":false,"paper_date":"2018-10-22","paper":"/paper/compositional-coding-capsule-network-with-k","paper_url":"https://arxiv.org/abs/1810.09177v5","paper_title":"Compositional Coding Capsule Network with K-Means Routing for Text Classification","code":"https://github.com/leftthomas/CCCapsNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Balanced+bi-leaf-RNN","metrics":{"Error":"7.9"},"uses_additional_data":false,"paper_date":"2018-08-29","paper":"/paper/on-tree-based-neural-sentence-modeling","paper_url":"http://arxiv.org/abs/1808.09644v1","paper_title":"On Tree-Based Neural Sentence Modeling","code":"https://github.com/ExplorerFreda/TreeEnc","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"VDCN","metrics":{"Error":"8.67"},"uses_additional_data":false,"paper_date":"2016-06-06","paper":"/paper/very-deep-convolutional-networks-for-text","paper_url":"http://arxiv.org/abs/1606.01781v2","paper_title":"Very Deep Convolutional Networks for Text Classification","code":"https://github.com/dongjun-Lee/text-classification-models-tf","n_code_links":24,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":18,"model":"SVDCNN","metrics":{"Error":"9.45"},"uses_additional_data":false,"paper_date":"2019-01-28","paper":"/paper/squeezed-very-deep-convolutional-neural","paper_url":"http://arxiv.org/abs/1901.09821v1","paper_title":"Squeezed Very Deep Convolutional Neural Networks for Text Classification","code":"https://github.com/lazarotm/SVDCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Char-level CNN","metrics":{"Error":"9.51"},"uses_additional_data":false,"paper_date":"2015-09-04","paper":"/paper/character-level-convolutional-networks-for","paper_url":"http://arxiv.org/abs/1509.01626v3","paper_title":"Character-level Convolutional Networks for Text Classification","code":"https://github.com/makcedward/nlpaug","n_code_links":30,"syntology":{"n_ran":4,"n_unverified":16,"n_samples":20,"n_pointer_only_licence":5}},{"rank_in_archive_order":20,"model":"Seq2CNN with GWS(50)","metrics":{"Error":"9.64"},"uses_additional_data":false,"paper_date":"2018-05-20","paper":"/paper/abstractive-text-classification-using","paper_url":"https://arxiv.org/abs/1805.07745v6","paper_title":"Abstractive Text Classification Using Sequence-to-convolution Neural Networks","code":"https://github.com/tgisaturday/Seq2CNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Llama-3.3-70B + CAPO","metrics":{"Error":"11.2"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"Qwen2.5-32B + CAPO","metrics":{"Error":"12.93"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"ToWE-SG","metrics":{"Error":"14.0"},"uses_additional_data":false,"paper_date":"2018-08-01","paper":"/paper/task-oriented-word-embedding-for-text","paper_url":"https://aclanthology.org/C18-1172","paper_title":"Task-oriented Word Embedding for Text Classification","code":"https://github.com/qianliu0708/ToWE","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Mistral-Small-24B + CAPO","metrics":{"Error":"15.7"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"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":11,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":34,"n_unverified":63,"n_samples":97,"n_pointer_only_licence":29,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":34,"n_unverified":63,"n_samples":97,"n_pointer_only_licence":29,"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"}}}