# Image Classification on CIFAR-100 (test) (Tracking Robustness Delta)

Source: [Image Classification on CIFAR-100 (test) (Tracking Robustness Delta)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta>)

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

Data updated: 2026-02-26T06:02:22.975Z

Evaluation of Image Classification performance on the CIFAR-100 test set, specifically tracking standard and robust accuracy changes across training steps (Best, Last, and Difference).

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 | Robust Accuracy (Best) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Robust Accuracy (Best)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Robust%20Accuracy%20(Best)>): Higher is better; unit: PERCENT.

- [Robust Accuracy (Last)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Robust%20Accuracy%20(Last)>): Higher is better; unit: PERCENT.

- [Robust Accuracy (Diff.)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Robust%20Accuracy%20(Diff.)>): Higher is better; unit: SCALAR.

- [Standard Accuracy (Best)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Standard%20Accuracy%20(Best)>): Higher is better; unit: PERCENT.

- [Standard Accuracy (Last)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Standard%20Accuracy%20(Last)>): Higher is better; unit: PERCENT.

- [Standard Accuracy (Diff.)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-tracking-robustness-delta.md?metric=Standard%20Accuracy%20(Diff.)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Robust Accuracy (Best) | Result date | Report paper |
| --- | --- | --- | --- |
| KD-AT-Auto | 26.36 | Not recorded | 68fa70d51e209131cea4d842 |
| KD-AT | 25.77 | Not recorded | 68fa70d51e209131cea4d842 |
| AT | 24.79 | Not recorded | 68fa70d51e209131cea4d842 |

### KD-AT-Auto

Robust Accuracy (Best): 26.36. Result ID: 69914ac43a6c314849071753.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d842.md>)

Recorded evaluation configuration: {"Setting":"KD-AT-Auto","T":"1.53\*","lambda":"0.83\*"}. This record does not assert independent reproduction.

### KD-AT

Robust Accuracy (Best): 25.77. Result ID: 69914ac43a6c314849071752.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d842.md>)

Recorded evaluation configuration: {"Setting":"KD-AT","T":2,"lambda":0.5}. This record does not assert independent reproduction.

### AT

Robust Accuracy (Best): 24.79. Result ID: 69914ac43a6c314849071751.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665a1e209131cea0fbae.md>)

Recorded evaluation configuration: {"Setting":"AT"}. This record does not assert independent reproduction.

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