Codesota · Computer Vision · Image Classification · CIFAR-10Tasks/Computer Vision/Image Classification
Image Classification · benchmark dataset · 2009 · EN

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.

Saturated benchmark

Benchmark near ceiling or stagnant — no meaningful SOTA movement in 2+ years

Paper ↗Download datasetSubmit a result ↵
§ 01 · Leaderboard

Best published scores.

9 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
accuracy· primary
9 rows
#ModelOrgSubmittedPaper / codeaccuracy
01Vision Transformer (ViT-H/14)—Oct 2020An Image is Worth 16x16 Words: Transformers for Image Re… · code99.50
02AIMv2 ViT-3B/14 448px—Nov 2024Multimodal Autoregressive Pre-training of Large Vision E… · code99.50
03BiT-L—Dec 2019Big Transfer (BiT): General Visual Representation Learni… · code99.37
04DeiT-B DistilledOpenMetaDec 2025meta-research99.10
05ConvNeXt V2 BaseOpenMetaDec 2025meta-research98.70
06LeJEPA ViT-L (304M)—Nov 2025LeJEPA: Provable and Scalable Self-Supervised Learning W… · code96.50
07ResNet-50OpenMicrosoftDec 2025cutout-paper96.01
08CN-CLIP—Nov 2022Chinese CLIP: Contrastive Vision-Language Pretraining in… · code96
09ResNet-110—Dec 2015Deep Residual Learning for Image Recognition · code93.57
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

3 steps
of state of the art.

Each row below marks a model that broke the previous record on accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · accuracy
  1. Dec 10, 2015ResNet-11093.57
  2. Dec 24, 2019BiT-L99.37
  3. Oct 22, 2020Vision Transformer (ViT-H/14)99.50
Fig 3 · SOTA-setting models only. 3 entries span Dec 2015 → Oct 2020.
§ 04 · Literature

6 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies