{"url":"/sota/language-modelling-on-hutter-prize","task":{"name":"Language Modelling","url":"/task/language-modelling","note":null},"dataset":{"name":"Hutter Prize","url":"/dataset/hutter-prize"},"category":"Natural Language Processing","categories":["Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.\r\n\r\nLarge language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model. \r\n\r\nSource: [Wikipedia](https://en.wikipedia.org/wiki/Language_model)","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":["Bit per Character (BPC)","Number of params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Bit per Character (BPC)":null,"Number of params":"lower"}},"counts":{"rows":18,"rows_with_code":18,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"Transformer-XL + RMS dynamic eval","metrics":{"Bit per Character (BPC)":"0.94","Number of params":"277M"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/dynamic-evaluation-of-transformer-language","paper_url":"http://arxiv.org/abs/1904.08378v1","paper_title":"Dynamic Evaluation of Transformer Language Models","code":"https://github.com/benkrause/dynamiceval-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Compressive Transformer","metrics":{"Bit per Character (BPC)":"0.97"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/compressive-transformers-for-long-range-1","paper_url":"https://arxiv.org/abs/1911.05507v1","paper_title":"Compressive Transformers for Long-Range Sequence Modelling","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Mogrifier LSTM + dynamic eval","metrics":{"Bit per Character (BPC)":"0.988","Number of params":"96M"},"uses_additional_data":false,"paper_date":"2019-09-04","paper":"/paper/mogrifier-lstm","paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","code":"https://github.com/deepmind/lamb","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"24-layer Transformer-XL","metrics":{"Bit per Character (BPC)":"0.99","Number of params":"277M"},"uses_additional_data":false,"paper_date":"2019-01-09","paper":"/paper/transformer-xl-attentive-language-models","paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":63,"n_unverified":80,"n_samples":143,"n_pointer_only_licence":43}},{"rank_in_archive_order":5,"model":"Longformer Large","metrics":{"Bit per Character (BPC)":"0.99","Number of params":"102M"},"uses_additional_data":false,"paper_date":"2020-04-10","paper":"/paper/longformer-the-long-document-transformer","paper_url":"https://arxiv.org/abs/2004.05150v2","paper_title":"Longformer: The Long-Document Transformer","code":"https://github.com/huggingface/transformers","n_code_links":22,"syntology":{"n_ran":15,"n_unverified":20,"n_samples":35,"n_pointer_only_licence":5}},{"rank_in_archive_order":6,"model":"Longformer Small","metrics":{"Bit per Character (BPC)":"1.00","Number of params":"41M"},"uses_additional_data":false,"paper_date":"2020-04-10","paper":"/paper/longformer-the-long-document-transformer","paper_url":"https://arxiv.org/abs/2004.05150v2","paper_title":"Longformer: The Long-Document Transformer","code":"https://github.com/huggingface/transformers","n_code_links":22,"syntology":{"n_ran":15,"n_unverified":20,"n_samples":35,"n_pointer_only_licence":5}},{"rank_in_archive_order":7,"model":"18-layer Transformer-XL","metrics":{"Bit per Character (BPC)":"1.03","Number of params":"88M"},"uses_additional_data":true,"paper_date":"2019-01-09","paper":"/paper/transformer-xl-attentive-language-models","paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":63,"n_unverified":80,"n_samples":143,"n_pointer_only_licence":43}},{"rank_in_archive_order":8,"model":"64-layer Character Transformer Model","metrics":{"Bit per Character (BPC)":"1.06","Number of params":"235M"},"uses_additional_data":false,"paper_date":"2018-08-09","paper":"/paper/character-level-language-modeling-with-deeper","paper_url":"http://arxiv.org/abs/1808.04444v2","paper_title":"Character-Level Language Modeling with Deeper Self-Attention","code":"https://github.com/facebookresearch/code-prediction-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"12-layer Transformer-XL","metrics":{"Bit per Character (BPC)":"1.06","Number of params":"41M"},"uses_additional_data":true,"paper_date":"2019-01-09","paper":"/paper/transformer-xl-attentive-language-models","paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":63,"n_unverified":80,"n_samples":143,"n_pointer_only_licence":43}},{"rank_in_archive_order":10,"model":"mLSTM + dynamic eval","metrics":{"Bit per Character (BPC)":"1.08","Number of params":"46M"},"uses_additional_data":false,"paper_date":"2017-09-21","paper":"/paper/dynamic-evaluation-of-neural-sequence-models","paper_url":"http://arxiv.org/abs/1709.07432v2","paper_title":"Dynamic Evaluation of Neural Sequence Models","code":"https://github.com/benkrause/dynamic-evaluation","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"12-layer Character Transformer Model","metrics":{"Bit per Character (BPC)":"1.11","Number of params":"44M"},"uses_additional_data":false,"paper_date":"2018-08-09","paper":"/paper/character-level-language-modeling-with-deeper","paper_url":"http://arxiv.org/abs/1808.04444v2","paper_title":"Character-Level Language Modeling with Deeper Self-Attention","code":"https://github.com/facebookresearch/code-prediction-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Mogrifier LSTM","metrics":{"Bit per Character (BPC)":"1.122","Number of params":"96M"},"uses_additional_data":false,"paper_date":"2019-09-04","paper":"/paper/mogrifier-lstm","paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","code":"https://github.com/deepmind/lamb","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"3-layer AWD-LSTM","metrics":{"Bit per Character (BPC)":"1.232","Number of params":"47M"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/an-analysis-of-neural-language-modeling-at","paper_url":"http://arxiv.org/abs/1803.08240v1","paper_title":"An Analysis of Neural Language Modeling at Multiple Scales","code":"https://github.com/salesforce/awd-lstm-lm","n_code_links":12,"syntology":{"n_ran":3,"n_unverified":15,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Large mLSTM +emb +WN +VD","metrics":{"Bit per Character (BPC)":"1.24","Number of params":"46M"},"uses_additional_data":false,"paper_date":"2016-09-26","paper":"/paper/multiplicative-lstm-for-sequence-modelling","paper_url":"http://arxiv.org/abs/1609.07959v3","paper_title":"Multiplicative LSTM for sequence modelling","code":"https://github.com/astakara48/python_project","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"Large FS-LSTM-4","metrics":{"Bit per Character (BPC)":"1.245","Number of params":"47M"},"uses_additional_data":false,"paper_date":"2017-05-24","paper":"/paper/fast-slow-recurrent-neural-networks","paper_url":"http://arxiv.org/abs/1705.08639v2","paper_title":"Fast-Slow Recurrent Neural Networks","code":"https://github.com/amujika/Fast-Slow-LSTM","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Large RHN","metrics":{"Bit per Character (BPC)":"1.27","Number of params":"46M"},"uses_additional_data":false,"paper_date":"2016-07-12","paper":"/paper/recurrent-highway-networks","paper_url":"http://arxiv.org/abs/1607.03474v5","paper_title":"Recurrent Highway Networks","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"FS-LSTM-4","metrics":{"Bit per Character (BPC)":"1.277","Number of params":"27M"},"uses_additional_data":false,"paper_date":"2017-05-24","paper":"/paper/fast-slow-recurrent-neural-networks","paper_url":"http://arxiv.org/abs/1705.08639v2","paper_title":"Fast-Slow Recurrent Neural Networks","code":"https://github.com/amujika/Fast-Slow-LSTM","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"RHN - depth 5 [zilly2016recurrent]","metrics":{"Bit per Character (BPC)":"1.31"},"uses_additional_data":false,"paper_date":"2016-07-12","paper":"/paper/recurrent-highway-networks","paper_url":"http://arxiv.org/abs/1607.03474v5","paper_title":"Recurrent Highway Networks","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":10,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":85,"n_unverified":128,"n_samples":213,"n_pointer_only_licence":48,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":227,"n_unverified":312,"n_samples":539,"n_pointer_only_licence":139,"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"}}}