# Semantic Textual Similarity on MedSTS Source: [Semantic Textual Similarity on MedSTS]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:40.536Z Evaluation of Semantic Textual Similarity performance using Pearson correlation on the MedSTS dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Semantic Textual Similarity | | Dataset (including any stated split) | MedSTS | | Metric | Pearson Correlation | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 17 of 17 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Pearson Correlation](): Higher is better; unit: SCALAR. ## Recorded results | Method | Pearson Correlation | Result date | Report paper | | --- | --- | --- | --- | | Original | 0.7598 | Not recorded | 68fa70731e209131cea4b188 | | CusText+ | 0.6316 | Not recorded | 68fa70731e209131cea4b188 | | CusText+ | 0.6213 | Not recorded | 68fa70731e209131cea4b188 | | CusText+ | 0.6172 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT+ | 0.5423 | Not recorded | 68fa70731e209131cea4b188 | | CusText | 0.5242 | Not recorded | 68fa70731e209131cea4b188 | | CusText | 0.5112 | Not recorded | 68fa70731e209131cea4b188 | | CusText | 0.4957 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT+ | 0.4271 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT+ | 0.4143 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT | 0.1673 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT | 0.1124 | Not recorded | 68fa70731e209131cea4b188 | | SANTEXT | 0.085 | Not recorded | 68fa70731e209131cea4b188 | | FBDD | 0.0411 | Not recorded | 68fa70731e209131cea4b188 | | Random | 0.0382 | Not recorded | 68fa70731e209131cea4b188 | | FBDD | 0.0368 | Not recorded | 68fa70731e209131cea4b188 | | FBDD | 0.0321 | Not recorded | 68fa70731e209131cea4b188 | ### Original Pearson Correlation: 0.7598. Result ID: 69911d7e3a6c31484905ced6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CusText+ Pearson Correlation: 0.6316. Result ID: 69911d7e3a6c31484905ced4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"2"}. This record does not assert independent reproduction. ### CusText+ Pearson Correlation: 0.6213. Result ID: 69911d7e3a6c31484905ced5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"3"}. This record does not assert independent reproduction. ### CusText+ Pearson Correlation: 0.6172. Result ID: 69911d7e3a6c31484905ced3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"1"}. This record does not assert independent reproduction. ### SANTEXT+ Pearson Correlation: 0.5423. Result ID: 69911d7e3a6c31484905ced2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"3"}. This record does not assert independent reproduction. ### CusText Pearson Correlation: 0.5242. Result ID: 69911d7e3a6c31484905cecf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"3"}. This record does not assert independent reproduction. ### CusText Pearson Correlation: 0.5112. Result ID: 69911d7e3a6c31484905cece. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"2"}. This record does not assert independent reproduction. ### CusText Pearson Correlation: 0.4957. Result ID: 69911d7e3a6c31484905cecd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon":"1"}. This record does not assert independent reproduction. ### SANTEXT+ Pearson Correlation: 0.4271. Result ID: 69911d7e3a6c31484905ced1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"2"}. This record does not assert independent reproduction. ### SANTEXT+ Pearson Correlation: 0.4143. Result ID: 69911d7e3a6c31484905ced0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"1"}. This record does not assert independent reproduction. ### SANTEXT Pearson Correlation: 0.1673. Result ID: 69911d7e3a6c31484905cecb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"2"}. This record does not assert independent reproduction. ### SANTEXT Pearson Correlation: 0.1124. Result ID: 69911d7e3a6c31484905cecc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"3"}. This record does not assert independent reproduction. ### SANTEXT Pearson Correlation: 0.085. Result ID: 69911d7e3a6c31484905ceca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"1"}. This record does not assert independent reproduction. ### FBDD Pearson Correlation: 0.0411. Result ID: 69911d7e3a6c31484905cec9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"3"}. This record does not assert independent reproduction. ### Random Pearson Correlation: 0.0382. Result ID: 69911d7e3a6c31484905cec6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FBDD Pearson Correlation: 0.0368. Result ID: 69911d7e3a6c31484905cec8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"2"}. This record does not assert independent reproduction. ### FBDD Pearson Correlation: 0.0321. Result ID: 69911d7e3a6c31484905cec7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.