# Image Classification on ImageNet Real 1.0 (test) Source: [Image Classification on ImageNet Real 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:59.534Z Evaluation of Image Classification performance on the test split of the ImageNet Real 1.0 dataset, reporting Top-1 accuracy. 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) | ImageNet Real 1.0 (test) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ViTAE-H | 91.2 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-L | 91.1 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-L | 90.8 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-H | 90.8 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-H | 90.7 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-L | 90.3 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViT-L | 90.1 | Not recorded | 68fa6e0c1e209131cea3dacf | | Swin-L | 90 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-B | 89.9 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViTAE-B | 89.4 | Not recorded | 68fa6e0c1e209131cea3dacf | | ViT-B | 89.1 | Not recorded | 68fa6e0c1e209131cea3dacf | | T2T-ViT-24 | 87.2 | Not recorded | 68fa6e0c1e209131cea3dacf | ### ViTAE-H Top-1 Accuracy: 91.2. Result ID: 698ff6d33a6c314849fd1faa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"644 M","Test size":"512","Pre-training/Method":"MAE"}. This record does not assert independent reproduction. ### ViTAE-L Top-1 Accuracy: 91.1. Result ID: 698ff6d33a6c314849fd1fa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"311 M","Test size":"384","Pre-training/Method":"MAE","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-L Top-1 Accuracy: 90.8. Result ID: 698ff6d33a6c314849fd1fa8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"311 M","Test size":"224","Pre-training/Method":"MAE","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-H Top-1 Accuracy: 90.8. Result ID: 698ff6d33a6c314849fd1fac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"644 M","Test size":"448","Pre-training/Method":"MAE","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-H Top-1 Accuracy: 90.7. Result ID: 698ff6d33a6c314849fd1fab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"644 M","Test size":"224","Pre-training/Method":"MAE","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-L Top-1 Accuracy: 90.3. Result ID: 698ff6d33a6c314849fd1fa7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"311 M","Test size":"224","Pre-training/Method":"MAE"}. This record does not assert independent reproduction. ### ViT-L Top-1 Accuracy: 90.1. Result ID: 698ff6d33a6c314849fd1fa6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"304 M","Test size":"224","Pre-training/Method":"MAE","Re-implemented":"true"}. This record does not assert independent reproduction. ### Swin-L Top-1 Accuracy: 90. Result ID: 698ff6d33a6c314849fd1fa5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"197 M","Test size":"384","Pre-training/Method":"Supervised","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-B Top-1 Accuracy: 89.9. Result ID: 698ff6d33a6c314849fd1fa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"89 M","Test size":"224","Pre-training/Method":"MAE","Fine-tuned on ImageNet-22K":"true"}. This record does not assert independent reproduction. ### ViTAE-B Top-1 Accuracy: 89.4. Result ID: 698ff6d33a6c314849fd1fa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"89 M","Test size":"224","Pre-training/Method":"MAE"}. This record does not assert independent reproduction. ### ViT-B Top-1 Accuracy: 89.1. Result ID: 698ff6d33a6c314849fd1fa2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"88 M","Test size":"224","Pre-training/Method":"MAE","Re-implemented":"true"}. This record does not assert independent reproduction. ### T2T-ViT-24 Top-1 Accuracy: 87.2. Result ID: 698ff6d33a6c314849fd1fa1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"65 M","Test size":"224","Pre-training/Method":"Supervised"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.