Browse › Natural Language Processing › Semantic Textual Similarity › STS Benchmark
STS Benchmark Benchmark (Semantic Textual Similarity)
Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.
Image source: Learning Semantic Textual Similarity from Conversations
The archive carries no text for this table; the description above is the archive's text for the task Semantic Textual Similarity. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Pearson Correlation (higher is better), Spearman Correlation (higher is better), Accuracy (higher is better), Dev Pearson Correlation (higher is better), Dev Spearman Correlation (higher is better). Points are placed at the row's paper date; 63 of 66 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | MT-DNN-SMART | 0.929 | 0.925 | – | Paper | Code | 2019 | 6 of 8 ran · 2 unverified | report | |||
| 2 | StructBERTRoBERTa ensemble | 0.928 | 0.924 | – | Paper | – | 2019 | no code linked | report | |||
| 3 | Mnet-Sim | 0.927 | 0.931 | – | Paper | – | 2021 | no code linked | report | |||
| 4 | T5-11B | 0.925 | 0.921 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | |||
| 5 | ALBERT | 0.925 | ✓ | Paper | Code | 2019 | 46 of 126 ran · 80 unverified | report | ||||
| 6 | XLNet (single model) | 0.925 | – | Paper | Code | 2019 | 10 of 24 ran · 14 unverified | report | ||||
| 7 | RoBERTa | 0.922 | – | Paper | Code | 2019 | 22 of 48 ran · 26 unverified | report | ||||
| 8 | ELECTRA | 0.921 | – | – | – | not matched | report | |||||
| 9 | RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned) | 0.919 | – | Paper | Code | 2022 | 2 of 5 ran · 3 unverified | report | ||||
| 10 | PSQ (Chen et al., 2020) | 0.919 | – | Paper | Code | 2020 | 1 of 4 ran · 3 unverified | report | ||||
| 11 | RoBERTa-large 355M + Entailment as Few-shot Learner | 0.918 | – | Paper | Code | 2021 | 1 of 3 ran · 2 unverified | report | ||||
| 12 | ERNIE 2.0 Large | 0.912 | – | Paper | Code | 2019 | 0 of 1 ran · 1 unverified | report | ||||
| 13 | Q-BERT (Shen et al., 2020) | 0.911 | – | Paper | – | 2019 | no code linked | report | ||||
| 14 | Q8BERT (Zafrir et al., 2019) | 0.911 | – | Paper | Code | 2019 | 3 of 11 ran · 8 unverified | report | ||||
| 15 | ELECTRA (no tricks) | 0.910 | – | – | – | not matched | report | |||||
| 16 | DistilBERT 66M | 0.907 | – | Paper | Code | 2019 | 19 of 27 ran · 8 unverified | report | ||||
| 17 | T5-3B | 0.906 | 0.898 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | |||
| 18 | MLM+ del-word | 0.905 | – | Paper | – | 2020 | no code linked | report | ||||
| 19 | RealFormer | 0.9011 | 0.8988 | – | Paper | Code | 2020 | linked, not harvested | report | |||
| 20 | T5-Large | 0.899 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | ||||
| 21 | SpanBERT | 0.899 | – | Paper | Code | 2019 | 3 of 15 ran · 12 unverified | report | ||||
| 22 | T5-Base | 0.894 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | ||||
| 23 | ERNIE 2.0 Base | 0.876 | – | Paper | Code | 2019 | 0 of 1 ran · 1 unverified | report | ||||
| 24 | Charformer-Tall | 0.873 | – | Paper | Code | 2021 | 7 of 10 ran · 3 unverified | report | ||||
| 25 | T5-Small | 0.856 | 0.85 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | |||
| 26 | ERNIE | 0.832 | – | Paper | Code | 2019 | 3 of 3 ran · 0 unverified | report | ||||
| 27 | 24hBERT | 0.820 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 28 | TinyBERT-4 14.5M | 0.799 | – | Paper | Code | 2019 | 0 of 4 ran · 4 unverified | report | ||||
| 29 | USE_T | 0.782 | – | Paper | Code | 2018 | 1 of 22 ran · 21 unverified | report | ||||
| 30 | AnglE-LLaMA-13B | 0.8969 | – | Paper | Code | 2023 | linked, not harvested | report | ||||
| 31 | ASA + RoBERTa | 0.892 | – | Paper | Code | 2022 | linked, not harvested | report | ||||
| 32 | PromptEOL+CSE+LLaMA-30B | 0.8914 | – | Paper | Code | 2023 | 4 of 4 ran · 0 unverified | report | ||||
| 33 | AnglE-LLaMA-7B | 0.8897 | – | Paper | Code | 2023 | linked, not harvested | report | ||||
| 34 | AnglE-LLaMA-7B-v2 | 0.8897 | – | Paper | Code | 2023 | linked, not harvested | report | ||||
| 35 | T5-Large 770M | 0.886 | – | Paper | Code | 2019 | 2 of 31 ran · 29 unverified | report | ||||
| 36 | PromptEOL+CSE+OPT-13B | 0.8856 | – | Paper | Code | 2023 | 4 of 4 ran · 0 unverified | report | ||||
| 37 | PromptEOL+CSE+OPT-2.7B | 0.8833 | – | Paper | Code | 2023 | 4 of 4 ran · 0 unverified | report | ||||
| 38 | PromCSE-RoBERTa-large (0.355B) | 0.8787 | – | Paper | Code | 2022 | linked, not harvested | report | ||||
| 39 | BigBird | .878 | – | Paper | Code | 2020 | 10 of 15 ran · 5 unverified | report | ||||
| 40 | SimCSE-RoBERTalarge | 0.867 | – | Paper | Code | 2021 | 17 of 30 ran · 13 unverified | report | ||||
| 41 | Trans-Encoder-RoBERTa-large-cross (unsup.) | 0.867 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 42 | Trans-Encoder-RoBERTa-large-bi (unsup.) | 0.8655 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 43 | BERT-LARGE | 0.865 | – | Paper | Code | 2018 | 204 of 659 ran · 455 unverified | report | ||||
| 44 | ASA + BERT-base | 0.865 | – | Paper | Code | 2022 | linked, not harvested | report | ||||
| 45 | Trans-Encoder-BERT-large-bi (unsup.) | 0.8616 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 46 | SRoBERTa-NLI-STSb-large | 0.8615 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 47 | SBERT-STSb-base | 0.8479 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 48 | Trans-Encoder-RoBERTa-base-cross (unsup.) | 0.8465 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 49 | SBERT-STSb-large | 0.8445 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 50 | FNet-Large | 0.84 | – | Paper | Code | 2021 | 2 of 2 ran · 0 unverified | report | ||||
| 51 | Trans-Encoder-BERT-base-bi (unsup.) | 0.839 | – | Paper | Code | 2021 | linked, not harvested | report | ||||
| 52 | Pearl | 0.7981 | – | – | – | not matched | report | |||||
| 53 | SBERT-NLI-large | 0.79 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 54 | Mirror-RoBERTa-base (unsup.) | 0.787 | – | Paper | Code | 2021 | 0 of 1 ran · 1 unverified | report | ||||
| 55 | Dino (STSb/̄🦕) | 0.7782 | – | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||
| 56 | SRoBERTa-NLI-base | 0.7777 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 57 | SBERT-NLI-base | 0.7703 | – | Paper | Code | 2019 | 20 of 58 ran · 38 unverified | report | ||||
| 58 | Dino (STS/̄🦕) | 0.7651 | – | Paper | Code | 2021 | 0 of 3 ran · 3 unverified | report | ||||
| 59 | Mirror-BERT-base (unsup.) | 0.764 | – | Paper | Code | 2021 | 0 of 1 ran · 1 unverified | report | ||||
| 60 | BERTlarge-flow (target) | 0.7226 | – | Paper | Code | 2020 | 3 of 3 ran · 0 unverified | report | ||||
| 61 | IS-BERT-NLI | 0.6921 | – | Paper | Code | 2020 | linked, not harvested | report | ||||
| 62 | Rematch | 0.6652 | – | Paper | Code | 2024 | linked, not harvested | report | ||||
| 63 | Def2Vec | 0.6372 | – | Paper | Code | 2023 | linked, not harvested | report | ||||
| 64 | DeBERTa (large) | 92.5 | – | Paper | Code | 2020 | 4 of 13 ran · 9 unverified | report | ||||
| 65 | SMARTRoBERTa | 92.8 | 92.6 | – | Paper | Code | 2019 | 6 of 8 ran · 2 unverified | report | |||
| 66 | SMART-BERT | 90.0 | 89.4 | – | Paper | Code | 2019 | 6 of 8 ran · 2 unverified | report |
All 66 rows shown. 63 link to a paper page on this site; 1 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 43 rows have a graph line, from 26 distinct papers; 36 rows (22 papers) have at least one sample that ran. Counting each paper once: Syntology ran 390 of 1,130 samples; 740 unverified. Separately, 262 of those 1,130 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections