# Image Classification on Seen Tasks (EuroSAT, SVHN, GTSRB, MNIST) (test) Source: [Image Classification on Seen Tasks (EuroSAT, SVHN, GTSRB, MNIST) (test)]() Collection index: [llms.txt]() Data updated: 2026-03-05T09:00:02.740Z Aggregate evaluation of Image Classification performance across the test splits of four datasets: EuroSAT, SVHN, GTSRB, and MNIST. 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 | Image Classification | | Dataset (including any stated split) | Seen Tasks (EuroSAT, SVHN, GTSRB, MNIST) (test) | | Metric | EuroSAT Accuracy | | 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 - [EuroSAT Accuracy](): Higher is better; unit: PERCENT. - [SVHN Accuracy](): Higher is better; unit: PERCENT. - [GTSRB Accuracy](): Higher is better; unit: PERCENT. - [MNIST Accuracy](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | EuroSAT Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BD-Merging | 97.13 | Not recorded | 69a90e142d603e6de3e408af | | Twin-Merging | 94.83 | Not recorded | 69a90e142d603e6de3e408af | | AdaMerging | 89.85 | Not recorded | 69a90e142d603e6de3e408af | | Task Arithmetic | 75.8 | Not recorded | 69a90e142d603e6de3e408af | | Ties-Merging | 70.85 | Not recorded | 69a90e142d603e6de3e408af | | Pretrained | 43.6 | Not recorded | 69a90e142d603e6de3e408af | ### BD-Merging EuroSAT Accuracy: 97.13. Result ID: 69a945fe6dbb7075b952e3ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Weights":"Layer-wise"}. This record does not assert independent reproduction. ### Twin-Merging EuroSAT Accuracy: 94.83. Result ID: 69a945fe6dbb7075b952e3aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Weights":"Layer-wise"}. This record does not assert independent reproduction. ### AdaMerging EuroSAT Accuracy: 89.85. Result ID: 69a945fe6dbb7075b952e3a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Weights":"Layer-wise"}. This record does not assert independent reproduction. ### Task Arithmetic EuroSAT Accuracy: 75.8. Result ID: 69a945fe6dbb7075b952e3a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Weights":"Layer-wise"}. This record does not assert independent reproduction. ### Ties-Merging EuroSAT Accuracy: 70.85. Result ID: 69a945fe6dbb7075b952e3a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Weights":"Layer-wise"}. This record does not assert independent reproduction. ### Pretrained EuroSAT Accuracy: 43.6. Result ID: 69a945fe6dbb7075b952e3a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.