Browse › Natural Language Processing › Semantic Textual Similarity › STS Benchmark

Semantic Textual Similarity archive 2025-07-28

STS Benchmark Benchmark (Semantic Textual Similarity)

66 rows 59 with code listed 5 metrics Dataset page

Syntology Since the archive (Syntology): none placed; 10 newer papers judged to report on this board so far.

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

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, not an evaluation date; 63 of 66 rows carry one.

The chart needs JavaScript; the table below carries every value.

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 0.9290.925 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
2 StructBERTRoBERTa ensemble 0.9280.924 – Paper – 2019 no code linked report
3 Mnet-Sim 0.9270.931 – Paper – 2021 no code linked report
4 T5-11B 0.9250.921 – Paper Code 2019 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
5 ALBERT 0.925 ✓ Paper Code 2019 official (archive's flag): 6 ran · 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified report
6 XLNet (single model) 0.925 – Paper Code 2019 official (archive's flag): 1 ran · 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified report
7 RoBERTa 0.922 – Paper Code 2019 community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified report
8 ELECTRA 0.921 – – – not matched report
9 RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned) 0.919 – Paper Code 2022 official: harvested, nothing ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
10 PSQ (Chen et al., 2020) 0.919 – Paper Code 2020 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified report
11 RoBERTa-large 355M + Entailment as Few-shot Learner 0.918 – Paper Code 2021 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
12 ERNIE 2.0 Large 0.912 – Paper Code 2019 official: harvested, nothing ran · 0 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 official (archive's flag): 5 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
15 ELECTRA (no tricks) 0.910 – – – not matched report
16 DistilBERT 66M 0.907 – Paper Code 2019 official (archive's flag): 1 ran · 21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified report
17 T5-3B 0.9060.898 – Paper Code 2019 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
18 MLM+ del-word 0.905 – Paper – 2020 no code linked report
19 RealFormer 0.90110.8988 – Paper Code 2020 linked, not harvested report
20 T5-Large 0.899 – Paper Code 2019 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
21 SpanBERT 0.899 – Paper Code 2019 official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified report
22 T5-Base 0.894 – Paper Code 2019 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
23 ERNIE 2.0 Base 0.876 – Paper Code 2019 official: harvested, nothing ran · 0 ran · 1 unverified report
24 Charformer-Tall 0.873 – Paper Code 2021 community repositories only · 7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified report
25 T5-Small 0.8560.85 – Paper Code 2019 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
26 ERNIE 0.832 – Paper Code 2019 official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
27 24hBERT 0.820 – Paper Code 2021 linked, not harvested report
28 TinyBERT-4 14.5M 0.799 – Paper Code 2019 official: harvested, nothing ran · 0 ran · 4 unverified report
29 USE_T 0.782 – Paper Code 2018 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 4 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 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 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 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified report
36 PromptEOL+CSE+OPT-13B 0.8856 – Paper Code 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
37 PromptEOL+CSE+OPT-2.7B 0.8833 – Paper Code 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
38 PromCSE-RoBERTa-large (0.355B) 0.8787 – Paper Code 2022 linked, not harvested report
39 BigBird .878 – Paper Code 2020 official (archive's flag): 1 ran · 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified report
40 SimCSE-RoBERTalarge 0.867 – Paper Code 2021 community repositories only · 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 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 official: no sample here; runs from other or unrecorded repositories · 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 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 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified report
47 SBERT-STSb-base 0.8479 – Paper Code 2019 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 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 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified report
50 FNet-Large 0.84 – Paper Code 2021 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 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 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified report
54 Mirror-RoBERTa-base (unsup.) 0.787 – Paper Code 2021 official: harvested, nothing ran · 0 ran · 1 unverified report
55 Dino (STSb/̄🦕) 0.7782 – Paper Code 2021 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
56 SRoBERTa-NLI-base 0.7777 – Paper Code 2019 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified report
57 SBERT-NLI-base 0.7703 – Paper Code 2019 community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified report
58 Dino (STS/̄🦕) 0.7651 – Paper Code 2021 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
59 Mirror-BERT-base (unsup.) 0.764 – Paper Code 2021 official: harvested, nothing ran · 0 ran · 1 unverified report
60 BERTlarge-flow (target) 0.7226 – Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 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 official: no sample here; runs from other or unrecorded repositories · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified report
65 SMARTRoBERTa 92.892.6 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
66 SMART-BERT 90.089.4 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 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 ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not 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. Rows whose paper has a sample that ran: 38 (37 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument). Papers: 23 with a sample that ran: 22 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 43 rows with a graph line, 35 have an archive-official repository: on 12 a sample from it ran (9 with a run with no instrument failure), on 12 the samples that ran came from community repositories only, and on 5 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 1,130 samples: 612 ran (of which 132 constructed an object rather than computing a result; 473 with no instrument failure: 45 honoured, 10 violated, 418 with no contract checked; 139 where Syntology's instrument failed) · 518 unverified. Separately, 291 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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 16 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,582 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 10 proposed a result; of those 10, 10 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices arXiv:2609.27982 23 Sep 2026 repository linked, no samples harvested refused by a rule: the value is not on the scale of the leaderboard column's archive values
The Embedder's Dilemma: LLMs Are Better, but at What Cost? arXiv:2608.12875 13 Aug 2026 3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs arXiv:2608.04488 5 Aug 2026 11 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models arXiv:2604.06291 7 Apr 2026 2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result refused by a rule: the value is not on the scale of the leaderboard column's archive values
RELISH: LLM REgression with a Latent Iterative State Head arXiv:2604.01206 1 Apr 2026 repository linked, no samples harvested refused by rules: the model pointed at a header row; the table, row or column pointed at does not exist
IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring arXiv:2603.13792 14 Mar 2026 held, no recorded run refused by a rule: the table's column header does not name the leaderboard's metric
LLM2Vec-Gen: Generative Embeddings from Large Language Models arXiv:2603.10913 11 Mar 2026 5 harvested: 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with... arXiv:2603.05960 6 Mar 2026 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified refused by a rule: the row label the model quoted is not the row's label
Towards Improved Sentence Representations using Token Graphs arXiv:2603.03389 3 Mar 2026 repository linked, no samples harvested refused by a rule: one configuration gave two values for one column
SemPA: Improving Sentence Embeddings of Large Language Models through Semantic... arXiv:2601.05075 8 Jan 2026 3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified refused by a rule: one configuration gave two values for one column

Syntology 10 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 10 counted above as giving no cell that passed the extractor's own checks are the 10 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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