# Image Classification on CIFAR-100 (Raw Accuracy and GRR)

Source: [Image Classification on CIFAR-100 (Raw Accuracy and GRR)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-raw-accuracy-and-grr>)

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

Data updated: 2026-06-19T06:42:59.287Z

Evaluation of standard Image Classification performance on the CIFAR-100 dataset, focusing on Raw Accuracy and the GRR metric.

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 | Raw Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Raw Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-raw-accuracy-and-grr.md?metric=Raw%20Accuracy>): Higher is better; unit: PERCENT.

- [GRR](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-raw-accuracy-and-grr.md?metric=GRR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Raw Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DiverseDistill | 92.88 | Not recorded | 68fa73361e209131cea5b314 |
| AutoSKDBert | 92.37 | Not recorded | 68fa73361e209131cea5b314 |
| MT | 92.28 | Not recorded | 68fa73361e209131cea5b314 |
| AMTML | 92 | Not recorded | 68fa73361e209131cea5b314 |
| AEKD | 91.72 | Not recorded | 68fa73361e209131cea5b314 |

### DiverseDistill

Raw Accuracy: 92.88. Result ID: 6a34e4bbfbc373592c319917.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

Recorded evaluation configuration: {"Committee":"CLIP + ViT\_L"}. This record does not assert independent reproduction.

### AutoSKDBert

Raw Accuracy: 92.37. Result ID: 6a34e4bbfbc373592c319915.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e071e209131cea3d811.md>)

Recorded evaluation configuration: {"Committee":"CLIP + ViT\_L"}. This record does not assert independent reproduction.

### MT

Raw Accuracy: 92.28. Result ID: 6a34e4bbfbc373592c319913.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

Recorded evaluation configuration: {"Committee":"CLIP + ViT\_L"}. This record does not assert independent reproduction.

### AMTML

Raw Accuracy: 92. Result ID: 6a34e4bbfbc373592c319914.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696f1e209131cea220aa.md>)

Recorded evaluation configuration: {"Committee":"CLIP + ViT\_L"}. This record does not assert independent reproduction.

### AEKD

Raw Accuracy: 91.72. Result ID: 6a34e4bbfbc373592c319916.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73361e209131cea5b314.md>)

Recorded evaluation configuration: {"Committee":"CLIP + ViT\_L"}. This record does not assert independent reproduction.

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