# Image Classification on ImageNet OOD (Avg of V2, R, Sketch, A, and ObjectNet) 1.0 (test)

Source: [Image Classification on ImageNet OOD (Avg of V2, R, Sketch, A, and ObjectNet) 1.0 (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-ood-avg-of-v2-r-sketch-a-and-objectnet-1-0-test>)

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

Data updated: 2026-02-26T06:06:48.568Z

Evaluation of Image Classification performance averaged across the ImageNet Out-of-Distribution test sets: V2, R, Sketch, A, and ObjectNet (Version 1.0).

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) | ImageNet OOD (Avg of V2, R, Sketch, A, and ObjectNet) 1.0 (test) |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Top-1 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-ood-avg-of-v2-r-sketch-a-and-objectnet-1-0-test.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| MonoSoup | 51.6 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| Uniform Model Soup | 51.4 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 51.37 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 50.91 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| Greedy Model Soup | 50.7 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| FT model (OOD+) | 50.67 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| ModelStock | 50.53 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 49.95 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 48.94 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| FT model (ID+) | 47.96 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 46.54 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| Initialization | 46.2 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 45.22 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 44.21 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| MonoSoup | 42.78 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| FT model (ID-) | 38.64 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |
| FT model (OOD-) | 36.71 | Not recorded | 698c0d5ac97a0b3e3b5e13c7 |

### MonoSoup

Top-1 Acc: 51.6. Result ID: 6998cc345698665ec42fb98a.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"OOD+","Merging Hyperparameter (R)":0.8,"Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### Uniform Model Soup

Top-1 Acc: 51.4. Result ID: 6998cc345698665ec42fb984.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce11e209131cea3679c.md>)

[Implementation](<https://github.com/mlfoundations/model-soups>)

Recorded evaluation configuration: {"Cost (Checkpoints)":70}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 51.37. Result ID: 6998cc345698665ec42fb993.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Pair Selection":"ID+, OOD+","Cost (Checkpoints)":2}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 50.91. Result ID: 6998cc345698665ec42fb98b.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"OOD+","Merging Hyperparameter (R)":"Automated","Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### Greedy Model Soup

Top-1 Acc: 50.7. Result ID: 6998cc345698665ec42fb985.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce11e209131cea3679c.md>)

[Implementation](<https://github.com/mlfoundations/model-soups>)

Recorded evaluation configuration: {"Cost (Checkpoints)":70}. This record does not assert independent reproduction.

### FT model (OOD+)

Top-1 Acc: 50.67. Result ID: 6998cc345698665ec42fb986.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

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

### ModelStock

Top-1 Acc: 50.53. Result ID: 6998cc345698665ec42fb992.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce11e209131cea3679c.md>)

[Implementation](<https://github.com/mlfoundations/model-soups>)

Recorded evaluation configuration: {"Model Pair Selection":"ID+, OOD+","Cost (Checkpoints)":2}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 49.95. Result ID: 6998cc345698665ec42fb98e.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"ID+","Merging Hyperparameter (R)":0.8,"Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 48.94. Result ID: 6998cc345698665ec42fb98f.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"ID+","Merging Hyperparameter (R)":"Automated","Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### FT model (ID+)

Top-1 Acc: 47.96. Result ID: 6998cc345698665ec42fb988.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

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

### MonoSoup

Top-1 Acc: 46.54. Result ID: 6998cc345698665ec42fb990.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"ID-","Merging Hyperparameter (R)":0.8,"Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### Initialization

Top-1 Acc: 46.2. Result ID: 6998cc345698665ec42fb983.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

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

### MonoSoup

Top-1 Acc: 45.22. Result ID: 6998cc345698665ec42fb991.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"ID-","Merging Hyperparameter (R)":"Automated","Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 44.21. Result ID: 6998cc345698665ec42fb98c.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"OOD-","Merging Hyperparameter (R)":0.8,"Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### MonoSoup

Top-1 Acc: 42.78. Result ID: 6998cc345698665ec42fb98d.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

Recorded evaluation configuration: {"Model Variant":"OOD-","Merging Hyperparameter (R)":"Automated","Cost (Checkpoints)":1}. This record does not assert independent reproduction.

### FT model (ID-)

Top-1 Acc: 38.64. Result ID: 6998cc345698665ec42fb989.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

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

### FT model (OOD-)

Top-1 Acc: 36.71. Result ID: 6998cc345698665ec42fb987.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d5ac97a0b3e3b5e13c7.md>)

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.
