Semantic Textual Similarity on SICK

Metric: Spearman Correlation (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Spearman Correlation▼	Extra Data	Paper	Date↕	Code
1	PromCSE-RoBERTa-large (0.355B)	0.8243	No	Improved Universal Sentence Embeddings with Prom...	2022-03-14	Code
2	PromptEOL+CSE+LLaMA-30B	0.8238	No	Scaling Sentence Embeddings with Large Language ...	2023-07-31	Code
3	PromptEOL+CSE+OPT-13B	0.8206	No	Scaling Sentence Embeddings with Large Language ...	2023-07-31	Code
4	SimCSE-RoBERTalarge	0.8195	No	SimCSE: Simple Contrastive Learning of Sentence ...	2021-04-18	Code
5	PromptEOL+CSE+OPT-2.7B	0.8129	No	Scaling Sentence Embeddings with Large Language ...	2023-07-31	Code
6	SentenceBERT	0.7462	Yes	Sentence-BERT: Sentence Embeddings using Siamese...	2019-08-27	Code
7	SRoBERTa-NLI-base	0.7446	No	Sentence-BERT: Sentence Embeddings using Siamese...	2019-08-27	Code
8	SRoBERTa-NLI-large	0.7429	No	Sentence-BERT: Sentence Embeddings using Siamese...	2019-08-27	Code
9	Dino (STS/̄🦕)	0.7426	No	Generating Datasets with Pretrained Language Mod...	2021-04-15	Code
10	SBERT-NLI-large	0.7375	No	Sentence-BERT: Sentence Embeddings using Siamese...	2019-08-27	Code
11	SBERT-NLI-base	0.7291	No	Sentence-BERT: Sentence Embeddings using Siamese...	2019-08-27	Code
12	Trans-Encoder-BERT-base-bi (unsup.)	0.7276	No	Trans-Encoder: Unsupervised sentence-pair modell...	2021-09-27	Code
13	Trans-Encoder-BERT-large-cross (unsup.)	0.7192	No	Trans-Encoder: Unsupervised sentence-pair modell...	2021-09-27	Code
14	Trans-Encoder-RoBERTa-large-cross (unsup.)	0.7163	No	Trans-Encoder: Unsupervised sentence-pair modell...	2021-09-27	Code
15	Trans-Encoder-BERT-large-bi (unsup.)	0.7133	No	Trans-Encoder: Unsupervised sentence-pair modell...	2021-09-27	Code
16	Mirror-RoBERTa-base (unsup.)	0.706	No	Fast, Effective, and Self-Supervised: Transformi...	2021-04-16	Code
17	Mirror-BERT-base (unsup.)	0.703	No	Fast, Effective, and Self-Supervised: Transformi...	2021-04-16	Code
18	Trans-Encoder-BERT-base-cross (unsup.)	0.6952	No	Trans-Encoder: Unsupervised sentence-pair modell...	2021-09-27	Code
19	Dino (STSb/̄🦕)	0.6809	No	Generating Datasets with Pretrained Language Mod...	2021-04-15	Code
20	Rematch	0.6772	No	Rematch: Robust and Efficient Matching of Local ...	2024-04-02	Code
21	BERTbase-flow (NLI)	0.6544	No	On the Sentence Embeddings from Pre-trained Lang...	2020-11-02	Code
22	IS-BERT-NLI	0.6425	No	An Unsupervised Sentence Embedding Method by Mut...	2020-09-25	Code

#1PromCSE-RoBERTa-large (0.355B)SOTA
0.8243
Spearman Correlation· 2022-03-14
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning Code
#2PromptEOL+CSE+LLaMA-30B
0.8238
Spearman Correlation· 2023-07-31
Scaling Sentence Embeddings with Large Language Models Code
#3PromptEOL+CSE+OPT-13B
0.8206
Spearman Correlation· 2023-07-31
Scaling Sentence Embeddings with Large Language Models Code
#4SimCSE-RoBERTalargeSOTA
0.8195
Spearman Correlation· 2021-04-18
SimCSE: Simple Contrastive Learning of Sentence Embeddings Code
#5PromptEOL+CSE+OPT-2.7B
0.8129
Spearman Correlation· 2023-07-31
Scaling Sentence Embeddings with Large Language Models Code
#6SentenceBERTSOTA
0.7462
Spearman Correlation· Extra Data· 2019-08-27
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Code
#7SRoBERTa-NLI-base
0.7446
Spearman Correlation· 2019-08-27
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Code
#8SRoBERTa-NLI-large
0.7429
Spearman Correlation· 2019-08-27
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Code
#9Dino (STS/̄🦕)
0.7426
Spearman Correlation· 2021-04-15
Generating Datasets with Pretrained Language Models Code
#10SBERT-NLI-large
0.7375
Spearman Correlation· 2019-08-27
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Code
#11SBERT-NLI-base
0.7291
Spearman Correlation· 2019-08-27
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Code
#12Trans-Encoder-BERT-base-bi (unsup.)
0.7276
Spearman Correlation· 2021-09-27
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations Code
#13Trans-Encoder-BERT-large-cross (unsup.)
0.7192
Spearman Correlation· 2021-09-27
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations Code
#14Trans-Encoder-RoBERTa-large-cross (unsup.)
0.7163
Spearman Correlation· 2021-09-27
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations Code
#15Trans-Encoder-BERT-large-bi (unsup.)
0.7133
Spearman Correlation· 2021-09-27
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations Code
#16Mirror-RoBERTa-base (unsup.)
0.706
Spearman Correlation· 2021-04-16
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders Code
#17Mirror-BERT-base (unsup.)
0.703
Spearman Correlation· 2021-04-16
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders Code
#18Trans-Encoder-BERT-base-cross (unsup.)
0.6952
Spearman Correlation· 2021-09-27
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations Code
#19Dino (STSb/̄🦕)
0.6809
Spearman Correlation· 2021-04-15
Generating Datasets with Pretrained Language Models Code
#20Rematch
0.6772
Spearman Correlation· 2024-04-02
Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity Code
#21BERTbase-flow (NLI)
0.6544
Spearman Correlation· 2020-11-02
On the Sentence Embeddings from Pre-trained Language Models Code
#22IS-BERT-NLI
0.6425
Spearman Correlation· 2020-09-25
An Unsupervised Sentence Embedding Method by Mutual Information Maximization Code