# Image Classification on CIFAR-100 resized to 224x224 (test) Source: [Image Classification on CIFAR-100 resized to 224x224 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:38.278Z Evaluation of Image Classification performance on the CIFAR-100 test set using inputs resized to 224x224 resolution. 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) | CIFAR-100 resized to 224 × 224 (test) | | Metric | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BEiT large | 88.4 | Not recorded | 68fa6e1b1e209131cea3dce4 | | BEiT large | 87.7 | Not recorded | 68fa6e1b1e209131cea3dce4 | | BEiT large | 86.2 | Not recorded | 68fa6e1b1e209131cea3dce4 | | BEiT large | 83 | Not recorded | 68fa6e1b1e209131cea3dce4 | | De et al. | 81.8 | Not recorded | 68fa6e1b1e209131cea3dce4 | | De et al. | 79.2 | Not recorded | 68fa6e1b1e209131cea3dce4 | | CrossViT base | 77.8 | Not recorded | 68fa6e1b1e209131cea3dce4 | | CrossViT base | 76.7 | Not recorded | 68fa6e1b1e209131cea3dce4 | | De et al. | 74.7 | Not recorded | 68fa6e1b1e209131cea3dce4 | | CrossViT base | 74.3 | Not recorded | 68fa6e1b1e209131cea3dce4 | | CrossViT base | 71.9 | Not recorded | 68fa6e1b1e209131cea3dce4 | | De et al. | 67.4 | Not recorded | 68fa6e1b1e209131cea3dce4 | ### BEiT large Accuracy: 88.4. Result ID: 699002963a6c314849fd7291. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"8","pretrained\_dataset":"ImageNet21k","parameters":"303M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### BEiT large Accuracy: 87.7. Result ID: 699002963a6c314849fd7290. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"4","pretrained\_dataset":"ImageNet21k","parameters":"303M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### BEiT large Accuracy: 86.2. Result ID: 699002963a6c314849fd728f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"2","pretrained\_dataset":"ImageNet21k","parameters":"303M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### BEiT large Accuracy: 83. Result ID: 699002963a6c314849fd728e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"1","pretrained\_dataset":"ImageNet21k","parameters":"303M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### De et al. Accuracy: 81.8. Result ID: 699002963a6c314849fd7289. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"8","pretrained\_dataset":"ImageNet1k"}. This record does not assert independent reproduction. ### De et al. Accuracy: 79.2. Result ID: 699002963a6c314849fd7288. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"4","pretrained\_dataset":"ImageNet1k"}. This record does not assert independent reproduction. ### CrossViT base Accuracy: 77.8. Result ID: 699002963a6c314849fd728d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"8","pretrained\_dataset":"ImageNet1k","parameters":"104M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### CrossViT base Accuracy: 76.7. Result ID: 699002963a6c314849fd728c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"4","pretrained\_dataset":"ImageNet1k","parameters":"104M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### De et al. Accuracy: 74.7. Result ID: 699002963a6c314849fd7287. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"2","pretrained\_dataset":"ImageNet1k"}. This record does not assert independent reproduction. ### CrossViT base Accuracy: 74.3. Result ID: 699002963a6c314849fd728b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"2","pretrained\_dataset":"ImageNet1k","parameters":"104M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### CrossViT base Accuracy: 71.9. Result ID: 699002963a6c314849fd728a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"1","pretrained\_dataset":"ImageNet1k","parameters":"104M","clipping\_method":"mixed ghost clipping"}. This record does not assert independent reproduction. ### De et al. Accuracy: 67.4. Result ID: 699002963a6c314849fd7286. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"epsilon (ε)":"1","pretrained\_dataset":"ImageNet1k"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.