# Image Classification on ImageNet30 (test)

Source: [Image Classification on ImageNet30 (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test>)

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

Data updated: 2026-02-26T05:36:01.478Z

Evaluation of Image Classification performance on the test split of the ImageNet30 dataset, measured using averaged accuracy across six severity levels (0 to 5).

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) | ImageNet30 (test) |
| Metric | Averaged Accuracy (Severity 0) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Averaged Accuracy (Severity 0)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%200)>): Higher is better; unit: PERCENT.

- [Averaged Accuracy (Severity 1)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%201)>): Higher is better; unit: PERCENT.

- [Averaged Accuracy (Severity 2)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%202)>): Higher is better; unit: PERCENT.

- [Averaged Accuracy (Severity 3)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%203)>): Higher is better; unit: PERCENT.

- [Averaged Accuracy (Severity 4)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%204)>): Higher is better; unit: PERCENT.

- [Averaged Accuracy (Severity 5)](<https://www.sota2.com/research/sota/image-classification-on-imagenet30-test.md?metric=Averaged%20Accuracy%20(Severity%205)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Averaged Accuracy (Severity 0) | Result date | Report paper |
| --- | --- | --- | --- |
| EIIL | 88.2 | Not recorded | 69535c9a53fdd5c36173db85 |
| SharpDRO | 87.5 | Not recorded | 69535c9a53fdd5c36173db85 |
| JTT | 87.3 | Not recorded | 69535c9a53fdd5c36173db85 |
| SharpDRO | 87.1 | Not recorded | 69535c9a53fdd5c36173db85 |
| JTT | 86.5 | Not recorded | 69535c9a53fdd5c36173db85 |
| EIIL | 85.5 | Not recorded | 69535c9a53fdd5c36173db85 |

### EIIL

Averaged Accuracy (Severity 0): 88.2. Result ID: 6999344b5698665ec49d5c4e.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5f1e209131cea27cee.md>)

Recorded evaluation configuration: {"Corruption Type":"Gaussian"}. This record does not assert independent reproduction.

### SharpDRO

Averaged Accuracy (Severity 0): 87.5. Result ID: 6999344b5698665ec49d5c4f.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Corruption Type":"Gaussian"}. This record does not assert independent reproduction.

### JTT

Averaged Accuracy (Severity 0): 87.3. Result ID: 6999344b5698665ec49d5c4d.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ade1e209131cea2aeeb.md>)

Recorded evaluation configuration: {"Corruption Type":"Gaussian"}. This record does not assert independent reproduction.

### SharpDRO

Averaged Accuracy (Severity 0): 87.1. Result ID: 6999344b5698665ec49d5c52.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

Recorded evaluation configuration: {"Corruption Type":"Shot"}. This record does not assert independent reproduction.

### JTT

Averaged Accuracy (Severity 0): 86.5. Result ID: 6999344b5698665ec49d5c50.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ade1e209131cea2aeeb.md>)

Recorded evaluation configuration: {"Corruption Type":"Shot"}. This record does not assert independent reproduction.

### EIIL

Averaged Accuracy (Severity 0): 85.5. Result ID: 6999344b5698665ec49d5c51.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9a53fdd5c36173db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5f1e209131cea27cee.md>)

Recorded evaluation configuration: {"Corruption Type":"Shot"}. This record does not assert independent reproduction.

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