# Image Classification on ImageNet-1K Regular (val) Source: [Image Classification on ImageNet-1K Regular (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:10.803Z Evaluation of Image Classification performance on the regular validation split of ImageNet-1K, 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-1K Regular (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Swin-B | 0.845 | Not recorded | 68fa6a8c1e209131cea28b62 | | EffNet-B7 | 0.843 | Not recorded | 68fa6a8c1e209131cea28b62 | | EffNet-B6 | 0.84 | Not recorded | 68fa6a8c1e209131cea28b62 | | EffNet-B5 | 0.836 | Not recorded | 68fa6a8c1e209131cea28b62 | | Swin-B | 0.835 | Not recorded | 68fa6a8c1e209131cea28b62 | | DeiT-B | 0.831 | Not recorded | 68fa6a8c1e209131cea28b62 | | Swin-S | 0.83 | Not recorded | 68fa6a8c1e209131cea28b62 | | RegNetY-16G | 0.829 | Not recorded | 68fa6a8c1e209131cea28b62 | | EffNet-B4 | 0.829 | Not recorded | 68fa6a8c1e209131cea28b62 | | DeiT-B | 0.818 | Not recorded | 68fa6a8c1e209131cea28b62 | | RegNetY-8G | 0.817 | Not recorded | 68fa6a8c1e209131cea28b62 | | EffNet-B3 | 0.816 | Not recorded | 68fa6a8c1e209131cea28b62 | | Swin-T | 0.813 | Not recorded | 68fa6a8c1e209131cea28b62 | | RegNetY-4G | 0.8 | Not recorded | 68fa6a8c1e209131cea28b62 | | DeiT-S | 0.798 | Not recorded | 68fa6a8c1e209131cea28b62 | | ViT-B/16 | 0.779 | Not recorded | 68fa6a8c1e209131cea28b62 | | ViT-L/16 | 0.765 | Not recorded | 68fa6a8c1e209131cea28b62 | ### Swin-B Top-1 Accuracy: 0.845. Result ID: 699ab8035698665ec445f3ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"384x384","#param.":"88M","FLOPs":"47.0G","throughput (image/s)":"84.7"}. This record does not assert independent reproduction. ### EffNet-B7 Top-1 Accuracy: 0.843. Result ID: 699ab8035698665ec445f3c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"600x600","#param.":"66M","FLOPs":"37.0G","throughput (image/s)":"55.1"}. This record does not assert independent reproduction. ### EffNet-B6 Top-1 Accuracy: 0.84. Result ID: 699ab8035698665ec445f3c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"528x528","#param.":"43M","FLOPs":"19.0G","throughput (image/s)":"96.9"}. This record does not assert independent reproduction. ### EffNet-B5 Top-1 Accuracy: 0.836. Result ID: 699ab8035698665ec445f3bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"456x456","#param.":"30M","FLOPs":"9.9G","throughput (image/s)":"169.1"}. This record does not assert independent reproduction. ### Swin-B Top-1 Accuracy: 0.835. Result ID: 699ab8035698665ec445f3c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"88M","FLOPs":"15.4G","throughput (image/s)":"278.1"}. This record does not assert independent reproduction. ### DeiT-B Top-1 Accuracy: 0.831. Result ID: 699ab8035698665ec445f3c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"384x384","#param.":"86M","FLOPs":"55.4G","throughput (image/s)":"85.9"}. This record does not assert independent reproduction. ### Swin-S Top-1 Accuracy: 0.83. Result ID: 699ab8035698665ec445f3c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"50M","FLOPs":"8.7G","throughput (image/s)":"436.9"}. This record does not assert independent reproduction. ### RegNetY-16G Top-1 Accuracy: 0.829. Result ID: 699ab8035698665ec445f3bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"84M","FLOPs":"16.0G","throughput (image/s)":"334.7"}. This record does not assert independent reproduction. ### EffNet-B4 Top-1 Accuracy: 0.829. Result ID: 699ab8035698665ec445f3be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"380x380","#param.":"19M","FLOPs":"4.2G","throughput (image/s)":"349.4"}. This record does not assert independent reproduction. ### DeiT-B Top-1 Accuracy: 0.818. Result ID: 699ab8035698665ec445f3c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"86M","FLOPs":"17.5G","throughput (image/s)":"292.3"}. This record does not assert independent reproduction. ### RegNetY-8G Top-1 Accuracy: 0.817. Result ID: 699ab8035698665ec445f3bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"39M","FLOPs":"8.0G","throughput (image/s)":"591.6"}. This record does not assert independent reproduction. ### EffNet-B3 Top-1 Accuracy: 0.816. Result ID: 699ab8035698665ec445f3bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"300x300","#param.":"12M","FLOPs":"1.8G","throughput (image/s)":"732.1"}. This record does not assert independent reproduction. ### Swin-T Top-1 Accuracy: 0.813. Result ID: 699ab8035698665ec445f3c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"29M","FLOPs":"4.5G","throughput (image/s)":"755.2"}. This record does not assert independent reproduction. ### RegNetY-4G Top-1 Accuracy: 0.8. Result ID: 699ab8035698665ec445f3ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"21M","FLOPs":"4.0G","throughput (image/s)":"1156.7"}. This record does not assert independent reproduction. ### DeiT-S Top-1 Accuracy: 0.798. Result ID: 699ab8035698665ec445f3c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"224x224","#param.":"22M","FLOPs":"4.6G","throughput (image/s)":"940.4"}. This record does not assert independent reproduction. ### ViT-B/16 Top-1 Accuracy: 0.779. Result ID: 699ab8035698665ec445f3c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"384x384","#param.":"86M","FLOPs":"55.4G","throughput (image/s)":"85.9"}. This record does not assert independent reproduction. ### ViT-L/16 Top-1 Accuracy: 0.765. Result ID: 699ab8035698665ec445f3c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"image size":"384x384","#param.":"307M","FLOPs":"190.7G","throughput (image/s)":"27.3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.