# Time Series Geo-Localization on BuildingsBench US Source: [Time Series Geo-Localization on BuildingsBench US]() Collection index: [llms.txt]() Data updated: 2026-06-09T08:23:30.386Z Evaluation of Time Series Geo-Localization performance on the BuildingsBench US dataset, reporting accuracy thresholds at 1km, 10km, 25km, 200km, and 750km, alongside the Median Distance Error. 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 | Time Series Geo-Localization | | Dataset (including any stated split) | BuildingsBench US | | Metric | Accuracy @ 1km (Street) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Accuracy @ 1km (Street)](): Higher is better; unit: PERCENT. - [Accuracy @ 10km (Town)](): Higher is better; unit: PERCENT. - [Accuracy @ 25km (Metro Area)](): Higher is better; unit: PERCENT. - [Accuracy @ 200km (Region)](): Higher is better; unit: PERCENT. - [Accuracy @ 750km (Country)](): Higher is better; unit: PERCENT. - [Median Distance Error (km)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy @ 1km (Street) | Result date | Report paper | | --- | --- | --- | --- | | TimesNet | 14.155 | Not recorded | 6a279e4990966ade919bf933 | | GeoGNN | 11.17 | Not recorded | 6a279e4990966ade919bf933 | | Retrieval-NN | 1 | Not recorded | 6a279e4990966ade919bf933 | | Retrieval-LLM | 0.608 | Not recorded | 6a279e4990966ade919bf933 | | GeoCLIP | 0.418 | Not recorded | 6a279e4990966ade919bf933 | | Random Guess | 0.042 | Not recorded | 6a279e4990966ade919bf933 | ### TimesNet Accuracy @ 1km (Street): 14.155. Result ID: 6a27cceafbc373592c247fad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoGNN Accuracy @ 1km (Street): 11.17. Result ID: 6a27cceafbc373592c247fb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Retrieval-NN Accuracy @ 1km (Street): 1. Result ID: 6a27cceafbc373592c247fae. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Retrieval-LLM Accuracy @ 1km (Street): 0.608. Result ID: 6a27cceafbc373592c247faf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoCLIP Accuracy @ 1km (Street): 0.418. Result ID: 6a27cceafbc373592c247fb0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Random Guess Accuracy @ 1km (Street): 0.042. Result ID: 6a27cceafbc373592c247fac. [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.