CIFAR-10
Unknown
60K 32x32 color images in 10 classes. Classic small-scale image classification benchmark with 50K training and 10K test images.
Benchmark Stats
Models3
Papers3
Metrics1
SOTA History
Coming SoonVisual timeline of state-of-the-art progression over time will appear here.
accuracy
accuracy
Higher is better
| Rank | Model | Code | Score | Paper / Source |
|---|---|---|---|---|
| 1 | deit-b-distilled Near-SOTA on CIFAR-10 with transfer learning. | 99.1 | meta-research | |
| 2 | convnext-v2-base Strong CNN performance on small-scale benchmark. | 98.7 | meta-research | |
| 3 | resnet-50 With Cutout augmentation. | 96.01 | cutout-paper |