# OOD Detection on ImageNet-ES (test)

Source: [OOD Detection on ImageNet-ES (test)](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-es-test>)

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

Data updated: 2026-06-17T06:51:15.503Z

Evaluation of Out-of-Distribution (OOD) detection performance using the test split of the ImageNet-ES dataset, reporting metrics such as AUROC and FPR95.

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 | OOD Detection |
| Dataset (including any stated split) | ImageNet-ES (test) |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-es-test.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [FPR@95](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-es-test.md?metric=FPR%4095>): Lower is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| MM++ | 81.7 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| X-Maha† | 76.78 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| Maha++ | 73.51 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| rMaha++ | 71.9 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| rMaha | 71.3 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| ReAct | 69.57 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| Maha | 69.53 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| MSP | 69.35 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| Energy | 67.54 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| ODIN | 63.22 | Not recorded | 6a322a32d33dfb23e783ebf9 |
| KNN | 55.88 | Not recorded | 6a322a32d33dfb23e783ebf9 |

### MM++

AUROC: 81.7. Result ID: 6a32439efbc373592c2f29ec.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### X-Maha†

AUROC: 76.78. Result ID: 6a32439efbc373592c2f29eb.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### Maha++

AUROC: 73.51. Result ID: 6a32439efbc373592c2f29e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b81e209131cea7a08c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### rMaha++

AUROC: 71.9. Result ID: 6a32439efbc373592c2f29ea.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### rMaha

AUROC: 71.3. Result ID: 6a32439efbc373592c2f29e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2666a.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### ReAct

AUROC: 69.57. Result ID: 6a32439efbc373592c2f29e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d8b5.md>)

[Implementation](<https://github.com/deeplearning-wisc/react.git>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### Maha

AUROC: 69.53. Result ID: 6a32439efbc373592c2f29e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64f91e209131cea077ac.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### MSP

AUROC: 69.35. Result ID: 6a32439efbc373592c2f29e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### Energy

AUROC: 67.54. Result ID: 6a32439efbc373592c2f29e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24242.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### ODIN

AUROC: 63.22. Result ID: 6a32439efbc373592c2f29e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b26f.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

### KNN

AUROC: 55.88. Result ID: 6a32439efbc373592c2f29e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a32d33dfb23e783ebf9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2f1e209131cea3e69b.md>)

[Implementation](<https://github.com/deeplearning-wisc/knn-ood>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Dataset":"ImageNet-LT"}. This record does not assert independent reproduction.

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