# Image Classification on ImageNet full (val) Source: [Image Classification on ImageNet full (val)]() Collection index: [llms.txt]() Data updated: 2026-03-31T07:57:56.936Z Evaluation of Image Classification performance on the validation split of the full ImageNet dataset, typically reported using Top-1 and Top-5 error rates. 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 full (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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. - [Top-1 Error](): Lower is better; unit: PERCENT. - [Top-5 Error](): Lower is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Swin-L | 78.18 | Not recorded | 69cb54e10636e5bf4afc9cff | | ConvNeXt-L | 77.47 | Not recorded | 69cb54e10636e5bf4afc9cff | | Swin-L | 77.21 | Not recorded | 69cb54e10636e5bf4afc9cff | | ConvNeXt-B | 76.38 | Not recorded | 69cb54e10636e5bf4afc9cff | | ConvNeXt-L | 76.36 | Not recorded | 69cb54e10636e5bf4afc9cff | | Swin-B | 76.21 | Not recorded | 69cb54e10636e5bf4afc9cff | | ConvNeXt-B | 75.95 | Not recorded | 69cb54e10636e5bf4afc9cff | | Swin-B | 75.75 | Not recorded | 69cb54e10636e5bf4afc9cff | | ResNet-50 | 64.02 | Not recorded | 69cb54e10636e5bf4afc9cff | | ResNet-50 | 63.12 | Not recorded | 69cb54e10636e5bf4afc9cff | ### Swin-L Top-1 Accuracy: 78.18. Result ID: 69cb7e7b47f34ce924b39a24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"Base"}. This record does not assert independent reproduction. ### ConvNeXt-L Top-1 Accuracy: 77.47. Result ID: 69cb7e7b47f34ce924b39a20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"Base"}. This record does not assert independent reproduction. ### Swin-L Top-1 Accuracy: 77.21. Result ID: 69cb7e7b47f34ce924b39a25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"+ ET3"}. This record does not assert independent reproduction. ### ConvNeXt-B Top-1 Accuracy: 76.38. Result ID: 69cb7e7b47f34ce924b39a1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"Base"}. This record does not assert independent reproduction. ### ConvNeXt-L Top-1 Accuracy: 76.36. Result ID: 69cb7e7b47f34ce924b39a21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"+ ET3"}. This record does not assert independent reproduction. ### Swin-B Top-1 Accuracy: 76.21. Result ID: 69cb7e7b47f34ce924b39a22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"Base"}. This record does not assert independent reproduction. ### ConvNeXt-B Top-1 Accuracy: 75.95. Result ID: 69cb7e7b47f34ce924b39a1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"+ ET3"}. This record does not assert independent reproduction. ### Swin-B Top-1 Accuracy: 75.75. Result ID: 69cb7e7b47f34ce924b39a23. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"+ ET3"}. This record does not assert independent reproduction. ### ResNet-50 Top-1 Accuracy: 64.02. Result ID: 69cb7e7b47f34ce924b39a1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"Base"}. This record does not assert independent reproduction. ### ResNet-50 Top-1 Accuracy: 63.12. Result ID: 69cb7e7b47f34ce924b39a1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Defense":"+ ET3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.