{"url":"/sota/semantic-textual-similarity-on-sts-benchmark","task":{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","note":null},"dataset":{"name":"STS Benchmark","url":"/dataset/sts-benchmark"},"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":["Pearson Correlation","Spearman Correlation","Accuracy","Dev Pearson Correlation","Dev 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":{"Pearson Correlation":"higher","Spearman Correlation":"higher","Accuracy":"higher","Dev Pearson Correlation":"higher","Dev Spearman Correlation":"higher"}},"counts":{"rows":66,"rows_with_code":59,"rows_with_paper_page":63,"rows_dated":63,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"MT-DNN-SMART","metrics":{"Pearson Correlation":"0.929","Spearman Correlation":"0.925"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"StructBERTRoBERTa ensemble","metrics":{"Pearson Correlation":"0.928","Spearman Correlation":"0.924"},"uses_additional_data":false,"paper_date":"2019-08-13","paper":"/paper/structbert-incorporating-language-structures","paper_url":"https://arxiv.org/abs/1908.04577v3","paper_title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Mnet-Sim","metrics":{"Pearson Correlation":"0.927","Spearman Correlation":"0.931"},"uses_additional_data":false,"paper_date":"2021-11-09","paper":"/paper/mnet-sim-a-multi-layered-semantic-similarity-1","paper_url":"https://arxiv.org/abs/2111.05412v1","paper_title":"MNet-Sim: A Multi-layered Semantic Similarity Network to Evaluate Sentence Similarity","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"T5-11B","metrics":{"Pearson Correlation":"0.925","Spearman Correlation":"0.921"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ALBERT","metrics":{"Pearson Correlation":"0.925"},"uses_additional_data":true,"paper_date":"2019-09-26","paper":"/paper/albert-a-lite-bert-for-self-supervised","paper_url":"https://arxiv.org/abs/1909.11942v6","paper_title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","code":"https://github.com/huggingface/transformers","n_code_links":48,"syntology":{"n_ran":68,"n_unverified":58,"n_samples":126,"n_pointer_only_licence":22}},{"rank_in_archive_order":6,"model":"XLNet (single model)","metrics":{"Pearson Correlation":"0.925"},"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":7,"model":"RoBERTa","metrics":{"Pearson Correlation":"0.922"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","paper_url":"https://arxiv.org/abs/1907.11692v1","paper_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","code":"https://github.com/huggingface/transformers","n_code_links":67,"syntology":{"n_ran":37,"n_unverified":11,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":8,"model":"ELECTRA","metrics":{"Pearson Correlation":"0.921"},"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":9,"model":"RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned)","metrics":{"Pearson Correlation":"0.919"},"uses_additional_data":false,"paper_date":"2022-08-15","paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","paper_url":"https://arxiv.org/abs/2208.07339v2","paper_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","code":"https://github.com/timdettmers/bitsandbytes","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"PSQ (Chen et al., 2020)","metrics":{"Pearson Correlation":"0.919"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/a-statistical-framework-for-low-bitwidth","paper_url":"https://arxiv.org/abs/2010.14298v1","paper_title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","code":"https://github.com/cjf00000/StatQuant","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"RoBERTa-large 355M + Entailment as Few-shot Learner","metrics":{"Pearson Correlation":"0.918"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/entailment-as-few-shot-learner","paper_url":"https://arxiv.org/abs/2104.14690v1","paper_title":"Entailment as Few-Shot Learner","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"ERNIE 2.0 Large","metrics":{"Pearson Correlation":"0.912"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/ernie-20-a-continual-pre-training-framework","paper_url":"https://arxiv.org/abs/1907.12412v2","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"Q-BERT (Shen et al., 2020)","metrics":{"Pearson Correlation":"0.911"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/q-bert-hessian-based-ultra-low-precision","paper_url":"https://arxiv.org/abs/1909.05840v2","paper_title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"Q8BERT (Zafrir et al., 2019)","metrics":{"Pearson Correlation":"0.911"},"uses_additional_data":false,"paper_date":"2019-10-14","paper":"/paper/q8bert-quantized-8bit-bert","paper_url":"https://arxiv.org/abs/1910.06188v2","paper_title":"Q8BERT: Quantized 8Bit BERT","code":"https://github.com/NervanaSystems/nlp-architect/blob/master/nlp_architect/models/transformers/quantized_bert.py","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":15,"model":"ELECTRA (no tricks)","metrics":{"Pearson Correlation":"0.910"},"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":"DistilBERT 66M","metrics":{"Pearson Correlation":"0.907"},"uses_additional_data":false,"paper_date":"2019-10-02","paper":"/paper/distilbert-a-distilled-version-of-bert","paper_url":"https://arxiv.org/abs/1910.01108v4","paper_title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":20,"n_unverified":7,"n_samples":27,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"T5-3B","metrics":{"Pearson Correlation":"0.906","Spearman Correlation":"0.898"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"MLM+ del-word","metrics":{"Pearson Correlation":"0.905"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/clear-contrastive-learning-for-sentence","paper_url":"https://arxiv.org/abs/2012.15466v1","paper_title":"CLEAR: Contrastive Learning for Sentence Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"RealFormer","metrics":{"Pearson Correlation":"0.9011","Spearman Correlation":"0.8988"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/informer-transformer-likes-informed-attention","paper_url":"https://arxiv.org/abs/2012.11747v3","paper_title":"RealFormer: Transformer Likes Residual Attention","code":"https://github.com/google-research/google-research","n_code_links":5,"syntology":null},{"rank_in_archive_order":20,"model":"T5-Large","metrics":{"Pearson Correlation":"0.899"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"SpanBERT","metrics":{"Pearson Correlation":"0.899"},"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}},{"rank_in_archive_order":22,"model":"T5-Base","metrics":{"Pearson Correlation":"0.894"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"ERNIE 2.0 Base","metrics":{"Pearson Correlation":"0.876"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/ernie-20-a-continual-pre-training-framework","paper_url":"https://arxiv.org/abs/1907.12412v2","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":24,"model":"Charformer-Tall","metrics":{"Pearson Correlation":"0.873"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/charformer-fast-character-transformers-via","paper_url":"https://arxiv.org/abs/2106.12672v3","paper_title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"T5-Small","metrics":{"Pearson Correlation":"0.856","Spearman Correlation":"0.85"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"ERNIE","metrics":{"Pearson Correlation":"0.832"},"uses_additional_data":false,"paper_date":"2019-05-17","paper":"/paper/ernie-enhanced-language-representation-with","paper_url":"https://arxiv.org/abs/1905.07129v3","paper_title":"ERNIE: Enhanced Language Representation with Informative Entities","code":"https://github.com/thunlp/ERNIE","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"24hBERT","metrics":{"Pearson Correlation":"0.820"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/how-to-train-bert-with-an-academic-budget","paper_url":"https://arxiv.org/abs/2104.07705v2","paper_title":"How to Train BERT with an Academic Budget","code":"https://github.com/peteriz/academic-budget-bert","n_code_links":4,"syntology":null},{"rank_in_archive_order":28,"model":"TinyBERT-4 14.5M","metrics":{"Pearson Correlation":"0.799"},"uses_additional_data":false,"paper_date":"2019-09-23","paper":"/paper/190910351","paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":29,"model":"USE_T","metrics":{"Pearson Correlation":"0.782"},"uses_additional_data":false,"paper_date":"2018-03-29","paper":"/paper/universal-sentence-encoder","paper_url":"http://arxiv.org/abs/1803.11175v2","paper_title":"Universal Sentence Encoder","code":"https://github.com/facebookresearch/InferSent","n_code_links":24,"syntology":{"n_ran":1,"n_unverified":21,"n_samples":22,"n_pointer_only_licence":1}},{"rank_in_archive_order":30,"model":"AnglE-LLaMA-13B","metrics":{"Spearman Correlation":"0.8969"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/angle-optimized-text-embeddings","paper_url":"https://arxiv.org/abs/2309.12871v9","paper_title":"AnglE-optimized Text Embeddings","code":"https://github.com/SeanLee97/AnglE","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"ASA + RoBERTa","metrics":{"Spearman Correlation":"0.892"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"PromptEOL+CSE+LLaMA-30B","metrics":{"Spearman Correlation":"0.8914"},"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":33,"model":"AnglE-LLaMA-7B","metrics":{"Spearman Correlation":"0.8897"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/angle-optimized-text-embeddings","paper_url":"https://arxiv.org/abs/2309.12871v9","paper_title":"AnglE-optimized Text Embeddings","code":"https://github.com/SeanLee97/AnglE","n_code_links":2,"syntology":null},{"rank_in_archive_order":34,"model":"AnglE-LLaMA-7B-v2","metrics":{"Spearman Correlation":"0.8897"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/angle-optimized-text-embeddings","paper_url":"https://arxiv.org/abs/2309.12871v9","paper_title":"AnglE-optimized Text Embeddings","code":"https://github.com/SeanLee97/AnglE","n_code_links":2,"syntology":null},{"rank_in_archive_order":35,"model":"T5-Large 770M","metrics":{"Spearman Correlation":"0.886"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"PromptEOL+CSE+OPT-13B","metrics":{"Spearman Correlation":"0.8856"},"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":37,"model":"PromptEOL+CSE+OPT-2.7B","metrics":{"Spearman Correlation":"0.8833"},"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":38,"model":"PromCSE-RoBERTa-large (0.355B)","metrics":{"Spearman Correlation":"0.8787"},"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":39,"model":"BigBird","metrics":{"Spearman Correlation":".878"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/big-bird-transformers-for-longer-sequences","paper_url":"https://arxiv.org/abs/2007.14062v2","paper_title":"Big Bird: Transformers for Longer Sequences","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":11}},{"rank_in_archive_order":40,"model":"SimCSE-RoBERTalarge","metrics":{"Spearman Correlation":"0.867"},"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":41,"model":"Trans-Encoder-RoBERTa-large-cross (unsup.)","metrics":{"Spearman Correlation":"0.867"},"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":42,"model":"Trans-Encoder-RoBERTa-large-bi (unsup.)","metrics":{"Spearman Correlation":"0.8655"},"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":43,"model":"BERT-LARGE","metrics":{"Spearman Correlation":"0.865"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":208,"n_unverified":451,"n_samples":659,"n_pointer_only_licence":149}},{"rank_in_archive_order":44,"model":"ASA + BERT-base","metrics":{"Spearman Correlation":"0.865"},"uses_additional_data":false,"paper_date":"2022-06-25","paper":"/paper/adversarial-self-attention-for-language","paper_url":"https://arxiv.org/abs/2206.12608v3","paper_title":"Adversarial Self-Attention for Language Understanding","code":"https://github.com/gingasan/adversarialsa","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"Trans-Encoder-BERT-large-bi (unsup.)","metrics":{"Spearman Correlation":"0.8616"},"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":46,"model":"SRoBERTa-NLI-STSb-large","metrics":{"Spearman Correlation":"0.8615"},"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":47,"model":"SBERT-STSb-base","metrics":{"Spearman Correlation":"0.8479"},"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":48,"model":"Trans-Encoder-RoBERTa-base-cross (unsup.)","metrics":{"Spearman Correlation":"0.8465"},"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":49,"model":"SBERT-STSb-large","metrics":{"Spearman Correlation":"0.8445"},"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":50,"model":"FNet-Large","metrics":{"Spearman Correlation":"0.84"},"uses_additional_data":false,"paper_date":"2021-05-09","paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","paper_url":"https://arxiv.org/abs/2105.03824v4","paper_title":"FNet: Mixing Tokens with Fourier Transforms","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":51,"model":"Trans-Encoder-BERT-base-bi (unsup.)","metrics":{"Spearman Correlation":"0.839"},"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":52,"model":"Pearl","metrics":{"Spearman Correlation":"0.7981"},"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":53,"model":"SBERT-NLI-large","metrics":{"Spearman Correlation":"0.79"},"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":54,"model":"Mirror-RoBERTa-base (unsup.)","metrics":{"Spearman Correlation":"0.787"},"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":55,"model":"Dino (STSb/̄🦕)","metrics":{"Spearman Correlation":"0.7782"},"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":56,"model":"SRoBERTa-NLI-base","metrics":{"Spearman Correlation":"0.7777"},"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":57,"model":"SBERT-NLI-base","metrics":{"Spearman Correlation":"0.7703"},"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":58,"model":"Dino (STS/̄🦕)","metrics":{"Spearman Correlation":"0.7651"},"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":59,"model":"Mirror-BERT-base (unsup.)","metrics":{"Spearman Correlation":"0.764"},"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":60,"model":"BERTlarge-flow (target)","metrics":{"Spearman Correlation":"0.7226"},"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":61,"model":"IS-BERT-NLI","metrics":{"Spearman Correlation":"0.6921"},"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},{"rank_in_archive_order":62,"model":"Rematch","metrics":{"Spearman Correlation":"0.6652"},"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":63,"model":"Def2Vec","metrics":{"Spearman Correlation":"0.6372"},"uses_additional_data":false,"paper_date":"2023-12-16","paper":"/paper/def2vec-extensible-word-embeddings-from","paper_url":"https://aclanthology.org/2023.icnlsp-1.21","paper_title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","code":"https://github.com/IreneMorazzoni/def_2_vec_irene","n_code_links":2,"syntology":null},{"rank_in_archive_order":64,"model":"DeBERTa (large)","metrics":{"Accuracy":"92.5"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3}},{"rank_in_archive_order":65,"model":"SMARTRoBERTa","metrics":{"Dev Pearson Correlation":"92.8","Dev Spearman Correlation":"92.6"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":66,"model":"SMART-BERT","metrics":{"Dev Pearson Correlation":"90.0","Dev Spearman Correlation":"89.4"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}}],"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":43,"rows_with_any_sample_ran":38,"distinct_papers_with_graph_line":26,"distinct_papers_with_any_sample_ran":23,"samples_over_distinct_papers":{"n_ran":476,"n_unverified":654,"n_samples":1130,"n_pointer_only_licence":262,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":773,"n_unverified":831,"n_samples":1604,"n_pointer_only_licence":328,"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"}}}