Image Classification2009en
Canadian Institute for Advanced Research 10
60K 32x32 color images in 10 classes. Classic small-scale image classification benchmark with 50K training and 10K test images.
Current State of the Art
DeiT-B Distilled
Meta
99.1
accuracy
accuracy Progress Over Time
Showing 2 breakthroughs from Aug 2017 to Dec 2020
Key Milestones
Total Improvement
3.2%
Time Span
3y 5m
Breakthroughs
2
Current SOTA
99.1
Top Models Performance Comparison
Top 3 models ranked by accuracy
Best Score
99.1
Top Model
DeiT-B Distilled
Models Compared
3
Score Range
3.1
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | DeiT-B DistilledOpen Source Meta | 99.1 | Dec 2025 | |
| 2 | ConvNeXt V2 BaseOpen Source Meta | 98.7 | Dec 2025 | |
| 3 | ResNet-50Open Source Microsoft | 96.01 | Dec 2025 |