# Image Classification on CIFAR-100+ (test)

Source: [Image Classification on CIFAR-100+ (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-plus-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:42:14.004Z

Evaluation of Image Classification performance on the test split of the extended CIFAR-100+ dataset, reporting classification error rate.

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+ (test) |
| Metric | Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 16 of 16 |
| 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

- [Error Rate](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-plus-test.md?metric=Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| DenseNet-BC | 17.18 | Not recorded | 68fa63f31e209131cea01bfd |
| DenseNet-BC | 17.6 | Not recorded | 68fa63f31e209131cea01bfd |
| DenseNet | 19.25 | Not recorded | 68fa63f31e209131cea01bfd |
| DenseNet | 20.2 | Not recorded | 68fa63f31e209131cea01bfd |
| Wide ResNet | 20.5 | Not recorded | 68fa63f31e209131cea01bfd |
| Wide ResNet | 22.07 | Not recorded | 68fa63f31e209131cea01bfd |
| DenseNet-BC | 22.27 | Not recorded | 68fa63f31e209131cea01bfd |
| ResNet (pre-activation) | 22.71 | Not recorded | 68fa63f31e209131cea01bfd |
| FractalNet | 23.3 | Not recorded | 68fa63f31e209131cea01bfd |
| FractalNet with Dropout/Drop-path | 23.73 | Not recorded | 68fa63f31e209131cea01bfd |
| ResNet (pre-activation) | 24.33 | Not recorded | 68fa63f31e209131cea01bfd |
| DenseNet | 24.42 | Not recorded | 68fa63f31e209131cea01bfd |
| ResNet with Stochastic Depth | 24.58 | Not recorded | 68fa63f31e209131cea01bfd |
| ResNet (reported by \[13\]) | 27.22 | Not recorded | 68fa63f31e209131cea01bfd |
| Highway Network | 32.39 | Not recorded | 68fa63f31e209131cea01bfd |
| All-CNN | 33.71 | Not recorded | 68fa63f31e209131cea01bfd |

### DenseNet-BC

Error Rate: 17.18. Result ID: 698c0824f729bc7f68e7eb97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":40,"Depth":190,"Params":"25.6M"}. This record does not assert independent reproduction.

### DenseNet-BC

Error Rate: 17.6. Result ID: 698c0824f729bc7f68e7eb96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":24,"Depth":250,"Params":"15.3M"}. This record does not assert independent reproduction.

### DenseNet

Error Rate: 19.25. Result ID: 698c0824f729bc7f68e7eb94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":24,"Depth":100,"Params":"27.2M"}. This record does not assert independent reproduction.

### DenseNet

Error Rate: 20.2. Result ID: 698c0824f729bc7f68e7eb93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":12,"Depth":100,"Params":"7.0M"}. This record does not assert independent reproduction.

### Wide ResNet

Error Rate: 20.5. Result ID: 698c0824f729bc7f68e7eb8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63671e209131ce9fe70d.md>)

[Implementation](<https://github.com/szagoruyko/wide-residual-networks>)

Recorded evaluation configuration: {"Depth":28,"Params":"36.5M"}. This record does not assert independent reproduction.

### Wide ResNet

Error Rate: 22.07. Result ID: 698c0824f729bc7f68e7eb8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63671e209131ce9fe70d.md>)

[Implementation](<https://github.com/szagoruyko/wide-residual-networks>)

Recorded evaluation configuration: {"Depth":16,"Params":"11.0M"}. This record does not assert independent reproduction.

### DenseNet-BC

Error Rate: 22.27. Result ID: 698c0824f729bc7f68e7eb95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":12,"Depth":100,"Params":"0.8M"}. This record does not assert independent reproduction.

### ResNet (pre-activation)

Error Rate: 22.71. Result ID: 698c0824f729bc7f68e7eb91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a31e209131ce9fa708.md>)

[Implementation](<https://github.com/KaimingHe/resnet-1k-layers>)

Recorded evaluation configuration: {"Depth":1001,"Params":"10.2M"}. This record does not assert independent reproduction.

### FractalNet

Error Rate: 23.3. Result ID: 698c0824f729bc7f68e7eb8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe853.md>)

Recorded evaluation configuration: {"Depth":21,"Params":"38.6M"}. This record does not assert independent reproduction.

### FractalNet with Dropout/Drop-path

Error Rate: 23.73. Result ID: 698c0824f729bc7f68e7eb8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe853.md>)

Recorded evaluation configuration: {"Depth":21,"Params":"38.6M"}. This record does not assert independent reproduction.

### ResNet (pre-activation)

Error Rate: 24.33. Result ID: 698c0824f729bc7f68e7eb90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a31e209131ce9fa708.md>)

[Implementation](<https://github.com/KaimingHe/resnet-1k-layers>)

Recorded evaluation configuration: {"Depth":164,"Params":"1.7M"}. This record does not assert independent reproduction.

### DenseNet

Error Rate: 24.42. Result ID: 698c0824f729bc7f68e7eb92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Implementation](<https://github.com/liuzhuang13/DenseNet>)

Recorded evaluation configuration: {"Growth Rate (k)":12,"Depth":40,"Params":"1.0M"}. This record does not assert independent reproduction.

### ResNet with Stochastic Depth

Error Rate: 24.58. Result ID: 698c0824f729bc7f68e7eb8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa811.md>)

[Implementation](<https://github.com/yueatsprograms/Stochastic_Depth>)

Recorded evaluation configuration: {"Depth":110,"Params":"1.7M"}. This record does not assert independent reproduction.

### ResNet (reported by \[13\])

Error Rate: 27.22. Result ID: 698c0824f729bc7f68e7eb8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa811.md>)

[Implementation](<https://github.com/yueatsprograms/Stochastic_Depth>)

Recorded evaluation configuration: {"Depth":110,"Params":"1.7M"}. This record does not assert independent reproduction.

### Highway Network

Error Rate: 32.39. Result ID: 698c0824f729bc7f68e7eb89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622b1e209131ce9f7d4d.md>)

[Implementation](<http://people.idsia.ch/~rupesh/very_deep_learning/>)

Recorded evaluation configuration: {"Depth":"-","Params":"-"}. This record does not assert independent reproduction.

### All-CNN

Error Rate: 33.71. Result ID: 698c0824f729bc7f68e7eb88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f31e209131cea01bfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61d01e209131ce9f633d.md>)

Recorded evaluation configuration: {"Depth":"-","Params":"-"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.