# Blood Glucose Forecasting on AZT1D 30 min Prediction Horizon (test) Source: [Blood Glucose Forecasting on AZT1D 30 min Prediction Horizon (test)]() Collection index: [llms.txt]() Data updated: 2026-04-16T06:45:18.031Z Evaluation of models performing blood glucose forecasting using the AZT1D dataset with a 30-minute prediction horizon on the test split, assessed using RMSE and MAE. 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 | Blood Glucose Forecasting | | Dataset (including any stated split) | AZT1D 30 min Prediction Horizon (test) | | Metric | RMSE | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 5 of 5 | | 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 - [RMSE](): Lower is better; unit: SCALAR. - [MAE](): Lower is better; unit: SCALAR. ## Recorded results | Method | RMSE | Result date | Report paper | | --- | --- | --- | --- | | GlucoNet | 9.27 | Not recorded | 68fa775c1e209131cea72b7e | | LSTM + Small Transformer | 9.36 | Not recorded | 68fa775c1e209131cea72b7e | | LSTM + Large Transformer | 9.98 | Not recorded | 68fa775c1e209131cea72b7e | | GLIMMER | 14.46 | Not recorded | 68fa775c1e209131cea72b7e | | CNN–LSTM | 17.21 | Not recorded | 68fa775c1e209131cea72b7e | ### GlucoNet RMSE: 9.27. Result ID: 69e0856647f34ce924c9310b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Distillation":"True","Protocol":"Short-Term (ST)","Configuration":"(32, 16)"}. This record does not assert independent reproduction. ### LSTM + Small Transformer RMSE: 9.36. Result ID: 69e0856647f34ce924c93109. [Reporting paper]() Recorded evaluation configuration: {"Transformer Size":"Small"}. This record does not assert independent reproduction. ### LSTM + Large Transformer RMSE: 9.98. Result ID: 69e0856647f34ce924c9310a. [Reporting paper]() Recorded evaluation configuration: {"Transformer Size":"Large"}. This record does not assert independent reproduction. ### GLIMMER RMSE: 14.46. Result ID: 69e0856647f34ce924c93108. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CNN–LSTM RMSE: 17.21. Result ID: 69e0856647f34ce924c93107. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.