# Image Classification on CIFAR-100 (Label Subset Evaluation)

Source: [Image Classification on CIFAR-100 (Label Subset Evaluation)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-label-subset-evaluation>)

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

Data updated: 2026-02-26T05:42:21.693Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, specifically measuring error rates across different subsets of labels (400, 2500, and 10000 labels).

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 |
| Metric | Error Rate (10000 Labels) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 14 of 14 |
| 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 (10000 Labels)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-label-subset-evaluation.md?metric=Error%20Rate%20(10000%20Labels)>): Lower is better; unit: PERCENT.

- [Error Rate (400 Labels)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-label-subset-evaluation.md?metric=Error%20Rate%20(400%20Labels)>): Lower is better; unit: PERCENT.

- [Error Rate (2500 Labels)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-label-subset-evaluation.md?metric=Error%20Rate%20(2500%20Labels)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Error Rate (10000 Labels) | Result date | Report paper |
| --- | --- | --- | --- |
| Fully-Supervised | 19.3 | Not recorded | 68fa70f11e209131cea4e324 |
| ReMixMatch | 20.04 | Not recorded | 68fa70f11e209131cea4e324 |
| SimMatch + EPASS | 21.32 | Not recorded | 68fa70f11e209131cea4e324 |
| SimMatch | 21.5 | Not recorded | 68fa70f11e209131cea4e324 |
| FlexMatch | 21.75 | Not recorded | 68fa70f11e209131cea4e324 |
| FreeMatch | 21.81 | Not recorded | 68fa70f11e209131cea4e324 |
| SoftMatch | 21.86 | Not recorded | 68fa70f11e209131cea4e324 |
| Dash | 21.89 | Not recorded | 68fa70f11e209131cea4e324 |
| AdaMatch | 21.99 | Not recorded | 68fa70f11e209131cea4e324 |
| FixMatch | 22.06 | Not recorded | 68fa70f11e209131cea4e324 |
| CoMatch | 22.11 | Not recorded | 68fa70f11e209131cea4e324 |
| CoMatch + EPASS | 22.16 | Not recorded | 68fa70f11e209131cea4e324 |
| UDA | 23.59 | Not recorded | 68fa70f11e209131cea4e324 |
| MixMatch | 33.22 | Not recorded | 68fa70f11e209131cea4e324 |

### Fully-Supervised

Error Rate (10000 Labels): 19.3. Result ID: 699165213a6c31484907db1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ReMixMatch

Error Rate (10000 Labels): 20.04. Result ID: 699165213a6c31484907db13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SimMatch + EPASS

Error Rate (10000 Labels): 21.32. Result ID: 699165213a6c31484907db1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Implementation](<https://github.com/beandkay/EPASS>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SimMatch

Error Rate (10000 Labels): 21.5. Result ID: 699165213a6c31484907db18.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31a70.md>)

[Implementation](<https://github.com/KyleZheng1997/simmatch>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FlexMatch

Error Rate (10000 Labels): 21.75. Result ID: 699165213a6c31484907db15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbb1e209131cea2ff1d.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FreeMatch

Error Rate (10000 Labels): 21.81. Result ID: 699165213a6c31484907db1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e711e209131cea3fd15.md>)

[Implementation](<https://github.com/microsoft/Semi-supervised-learning>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SoftMatch

Error Rate (10000 Labels): 21.86. Result ID: 699165213a6c31484907db1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41dad.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Dash

Error Rate (10000 Labels): 21.89. Result ID: 699165213a6c31484907db16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa61e209131cea2970c.md>)

[Implementation](<https://github.com/google-research/fixmatch>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AdaMatch

Error Rate (10000 Labels): 21.99. Result ID: 699165213a6c31484907db19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c011e209131cea319a6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FixMatch

Error Rate (10000 Labels): 22.06. Result ID: 699165213a6c31484907db14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d61e209131cea1e896.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoMatch

Error Rate (10000 Labels): 22.11. Result ID: 699165213a6c31484907db17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69751e209131cea2238f.md>)

[Implementation](<https://github.com/salesforce/CoMatch/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoMatch + EPASS

Error Rate (10000 Labels): 22.16. Result ID: 699165213a6c31484907db1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Implementation](<https://github.com/beandkay/EPASS>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UDA

Error Rate (10000 Labels): 23.59. Result ID: 699165213a6c31484907db11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d69a.md>)

[Implementation](<https://github.com/google-research/uda>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MixMatch

Error Rate (10000 Labels): 33.22. Result ID: 699165213a6c31484907db12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e324.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66961e209131cea11261.md>)

[Implementation](<https://github.com/google-research/mixmatch>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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