{"url":"/sota/semantic-textual-similarity-on-sick","task":{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","note":null},"dataset":{"name":"SICK","url":"/dataset/sick"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Semantic textual similarity deals with determining how similar two pieces of texts are.\r\nThis can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.\r\n\r\nImage source: [Learning Semantic Textual Similarity from Conversations](https://arxiv.org/pdf/1804.07754.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":["Spearman Correlation"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Spearman Correlation":"higher"}},"counts":{"rows":22,"rows_with_code":22,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"PromCSE-RoBERTa-large (0.355B)","metrics":{"Spearman Correlation":"0.8243"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/deep-continuous-prompt-for-contrastive-1","paper_url":"https://arxiv.org/abs/2203.06875v2","paper_title":"Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning","code":"https://github.com/yjiangcm/promcse","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PromptEOL+CSE+LLaMA-30B","metrics":{"Spearman Correlation":"0.8238"},"uses_additional_data":false,"paper_date":"2023-07-31","paper":"/paper/scaling-sentence-embeddings-with-large","paper_url":"https://arxiv.org/abs/2307.16645v1","paper_title":"Scaling Sentence Embeddings with Large Language Models","code":"https://github.com/kongds/scaling_sentemb","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"PromptEOL+CSE+OPT-13B","metrics":{"Spearman Correlation":"0.8206"},"uses_additional_data":false,"paper_date":"2023-07-31","paper":"/paper/scaling-sentence-embeddings-with-large","paper_url":"https://arxiv.org/abs/2307.16645v1","paper_title":"Scaling Sentence Embeddings with Large Language Models","code":"https://github.com/kongds/scaling_sentemb","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":4,"model":"SimCSE-RoBERTalarge","metrics":{"Spearman Correlation":"0.8195"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/simcse-simple-contrastive-learning-of","paper_url":"https://arxiv.org/abs/2104.08821v4","paper_title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/text_matching/simcse","n_code_links":23,"syntology":{"n_ran":17,"n_unverified":13,"n_samples":30,"n_pointer_only_licence":19}},{"rank_in_archive_order":5,"model":"PromptEOL+CSE+OPT-2.7B","metrics":{"Spearman Correlation":"0.8129"},"uses_additional_data":false,"paper_date":"2023-07-31","paper":"/paper/scaling-sentence-embeddings-with-large","paper_url":"https://arxiv.org/abs/2307.16645v1","paper_title":"Scaling Sentence Embeddings with Large Language Models","code":"https://github.com/kongds/scaling_sentemb","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":6,"model":"SentenceBERT","metrics":{"Spearman Correlation":"0.7462"},"uses_additional_data":true,"paper_date":"2019-08-27","paper":"/paper/sentence-bert-sentence-embeddings-using","paper_url":"https://arxiv.org/abs/1908.10084v1","paper_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","code":"https://github.com/UKPLab/sentence-transformers","n_code_links":64,"syntology":{"n_ran":33,"n_unverified":25,"n_samples":58,"n_pointer_only_licence":11}},{"rank_in_archive_order":7,"model":"SRoBERTa-NLI-base","metrics":{"Spearman Correlation":"0.7446"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/sentence-bert-sentence-embeddings-using","paper_url":"https://arxiv.org/abs/1908.10084v1","paper_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","code":"https://github.com/UKPLab/sentence-transformers","n_code_links":64,"syntology":{"n_ran":33,"n_unverified":25,"n_samples":58,"n_pointer_only_licence":11}},{"rank_in_archive_order":8,"model":"SRoBERTa-NLI-large","metrics":{"Spearman Correlation":"0.7429"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/sentence-bert-sentence-embeddings-using","paper_url":"https://arxiv.org/abs/1908.10084v1","paper_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","code":"https://github.com/UKPLab/sentence-transformers","n_code_links":64,"syntology":{"n_ran":33,"n_unverified":25,"n_samples":58,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"Dino (STS/̄🦕)","metrics":{"Spearman Correlation":"0.7426"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/generating-datasets-with-pretrained-language","paper_url":"https://arxiv.org/abs/2104.07540v3","paper_title":"Generating Datasets with Pretrained Language Models","code":"https://github.com/timoschick/dino","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SBERT-NLI-large","metrics":{"Spearman Correlation":"0.7375"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/sentence-bert-sentence-embeddings-using","paper_url":"https://arxiv.org/abs/1908.10084v1","paper_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","code":"https://github.com/UKPLab/sentence-transformers","n_code_links":64,"syntology":{"n_ran":33,"n_unverified":25,"n_samples":58,"n_pointer_only_licence":11}},{"rank_in_archive_order":11,"model":"SBERT-NLI-base","metrics":{"Spearman Correlation":"0.7291"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/sentence-bert-sentence-embeddings-using","paper_url":"https://arxiv.org/abs/1908.10084v1","paper_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","code":"https://github.com/UKPLab/sentence-transformers","n_code_links":64,"syntology":{"n_ran":33,"n_unverified":25,"n_samples":58,"n_pointer_only_licence":11}},{"rank_in_archive_order":12,"model":"Trans-Encoder-BERT-base-bi (unsup.)","metrics":{"Spearman Correlation":"0.7276"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/trans-encoder-unsupervised-sentence-pair","paper_url":"https://arxiv.org/abs/2109.13059v4","paper_title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","code":"https://github.com/amzn/trans-encoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Trans-Encoder-BERT-large-cross (unsup.)","metrics":{"Spearman Correlation":"0.7192"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/trans-encoder-unsupervised-sentence-pair","paper_url":"https://arxiv.org/abs/2109.13059v4","paper_title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","code":"https://github.com/amzn/trans-encoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"Trans-Encoder-RoBERTa-large-cross (unsup.)","metrics":{"Spearman Correlation":"0.7163"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/trans-encoder-unsupervised-sentence-pair","paper_url":"https://arxiv.org/abs/2109.13059v4","paper_title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","code":"https://github.com/amzn/trans-encoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"Trans-Encoder-BERT-large-bi (unsup.)","metrics":{"Spearman Correlation":"0.7133"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/trans-encoder-unsupervised-sentence-pair","paper_url":"https://arxiv.org/abs/2109.13059v4","paper_title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","code":"https://github.com/amzn/trans-encoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Mirror-RoBERTa-base (unsup.)","metrics":{"Spearman Correlation":"0.706"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/fast-effective-and-self-supervised","paper_url":"https://arxiv.org/abs/2104.08027v2","paper_title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","code":"https://github.com/cambridgeltl/mirror-bert","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"Mirror-BERT-base (unsup.)","metrics":{"Spearman Correlation":"0.703"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/fast-effective-and-self-supervised","paper_url":"https://arxiv.org/abs/2104.08027v2","paper_title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","code":"https://github.com/cambridgeltl/mirror-bert","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Trans-Encoder-BERT-base-cross (unsup.)","metrics":{"Spearman Correlation":"0.6952"},"uses_additional_data":false,"paper_date":"2021-09-27","paper":"/paper/trans-encoder-unsupervised-sentence-pair","paper_url":"https://arxiv.org/abs/2109.13059v4","paper_title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","code":"https://github.com/amzn/trans-encoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Dino (STSb/̄🦕)","metrics":{"Spearman Correlation":"0.6809"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/generating-datasets-with-pretrained-language","paper_url":"https://arxiv.org/abs/2104.07540v3","paper_title":"Generating Datasets with Pretrained Language Models","code":"https://github.com/timoschick/dino","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"Rematch","metrics":{"Spearman Correlation":"0.6772"},"uses_additional_data":false,"paper_date":"2024-04-02","paper":"/paper/rematch-robust-and-efficient-matching-of","paper_url":"https://arxiv.org/abs/2404.02126v1","paper_title":"Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity","code":"https://github.com/osome-iu/Rematch-RARE","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"BERTbase-flow (NLI)","metrics":{"Spearman Correlation":"0.6544"},"uses_additional_data":false,"paper_date":"2020-11-02","paper":"/paper/on-the-sentence-embeddings-from-pre-trained","paper_url":"https://arxiv.org/abs/2011.05864v1","paper_title":"On the Sentence Embeddings from Pre-trained Language Models","code":"https://github.com/InsaneLife/dssm","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"IS-BERT-NLI","metrics":{"Spearman Correlation":"0.6425"},"uses_additional_data":false,"paper_date":"2020-09-25","paper":"/paper/an-unsupervised-sentence-embedding-method","paper_url":"https://arxiv.org/abs/2009.12061v2","paper_title":"An Unsupervised Sentence Embedding Method by Mutual Information Maximization","code":"https://github.com/yanzhangnlp/IS-BERT","n_code_links":1,"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 6,885 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":14,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":60,"n_unverified":39,"n_samples":99,"n_pointer_only_licence":34,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":203,"n_unverified":140,"n_samples":343,"n_pointer_only_licence":86,"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"}}}