# Image Classification on CIFAR-10 (test) (Top-1 Accuracy vs Batch Size) Source: [Image Classification on CIFAR-10 (test) (Top-1 Accuracy vs Batch Size)]() Collection index: [llms.txt]() Data updated: 2026-03-23T10:34:09.202Z Evaluation of Image Classification performance on the CIFAR-10 test set, reporting Top-1 accuracy measured across various batch sizes (64, 128, 256, 512, 1024). 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-10 (test) | | Metric | Top-1 Accuracy (BS=64) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 (BS=64)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (BS=128)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (BS=256)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (BS=512)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (BS=1024)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (BS=64) | Result date | Report paper | | --- | --- | --- | --- | | ViT-Small | 94 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ViT-Base | 93.7 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ViTRM | 92.6 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ResNet-50 | 92 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ResNet-34 | 90.8 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ResNet-18 | 90.5 | Not recorded | 69c0c90b0636e5bf4afc3c28 | | ViT-Large | 80.8 | Not recorded | 69c0c90b0636e5bf4afc3c28 | ### ViT-Small Top-1 Accuracy (BS=64): 94. Result ID: 69c1169447f34ce924a934c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"16.9M"}. This record does not assert independent reproduction. ### ViT-Base Top-1 Accuracy (BS=64): 93.7. Result ID: 69c1169447f34ce924a934ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"85.1M"}. This record does not assert independent reproduction. ### ViTRM Top-1 Accuracy (BS=64): 92.6. Result ID: 69c1169447f34ce924a934c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"3.6M"}. This record does not assert independent reproduction. ### ResNet-50 Top-1 Accuracy (BS=64): 92. Result ID: 69c1169447f34ce924a934ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"23.5M"}. This record does not assert independent reproduction. ### ResNet-34 Top-1 Accuracy (BS=64): 90.8. Result ID: 69c1169447f34ce924a934cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"21.3M"}. This record does not assert independent reproduction. ### ResNet-18 Top-1 Accuracy (BS=64): 90.5. Result ID: 69c1169447f34ce924a934cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"11.2M"}. This record does not assert independent reproduction. ### ViT-Large Top-1 Accuracy (BS=64): 80.8. Result ID: 69c1169447f34ce924a934cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"302.4M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.