# Image Classification on ImageNet-ReaL 1 (test)

Source: [Image Classification on ImageNet-ReaL 1 (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-real-1-test>)

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

Data updated: 2026-02-26T06:06:57.093Z

Evaluation of Image Classification performance on the test split of the ImageNet-ReaL 1 dataset, reporting Top-1 accuracy alongside hardware efficiency metrics like throughput and TPU core usage.

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-ReaL 1 (test) |
| Metric | Top-1 Accuracy |
| 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

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

- [Throughput (img/sec/core)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-real-1-test.md?metric=Throughput%20(img%2Fsec%2Fcore)>): Higher is better; unit: SCALAR.

- [TPUv3 Core-Days](<https://www.sota2.com/research/sota/image-classification-on-imagenet-real-1-test.md?metric=TPUv3%20Core-Days>): Lower is better; unit: TIME.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MPL | 91.12 | Not recorded | 68fa6a201e209131cea26207 |
| ViT-H/14 | 90.72 | Not recorded | 68fa6a201e209131cea26207 |
| BiT-R152x4 | 90.54 | Not recorded | 68fa6a201e209131cea26207 |
| Mixer-H/14 | 90.18 | Not recorded | 68fa6a201e209131cea26207 |
| ViT-L/16 | 88.62 | Not recorded | 68fa6a201e209131cea26207 |
| Mixer-L/16 | 87.86 | Not recorded | 68fa6a201e209131cea26207 |

### MPL

Top-1 Accuracy: 91.12. Result ID: 698e11bdffc3901de09a8f8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea2227c.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/meta_pseudo_labels>)

Recorded evaluation configuration: {"Pre-training dataset":"unlabelled or weakly labelled data (proprietary)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### ViT-H/14

Top-1 Accuracy: 90.72. Result ID: 698e11bdffc3901de09a8f8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Pre-training dataset":"JFT-300M (proprietary)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### BiT-R152x4

Top-1 Accuracy: 90.54. Result ID: 698e11bdffc3901de09a8f8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa677a1e209131cea16a7e.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/retinanet>)

Recorded evaluation configuration: {"Pre-training dataset":"JFT-300M (proprietary)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### Mixer-H/14

Top-1 Accuracy: 90.18. Result ID: 698e11bdffc3901de09a8f89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Pre-training dataset":"JFT-300M (proprietary)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### ViT-L/16

Top-1 Accuracy: 88.62. Result ID: 698e11bdffc3901de09a8f88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Pre-training dataset":"ImageNet-21k (public)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### Mixer-L/16

Top-1 Accuracy: 87.86. Result ID: 698e11bdffc3901de09a8f87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Pre-training dataset":"ImageNet-21k (public)","Resolution":"448","Evaluation protocol":"Fine-tuned"}. This record does not assert independent reproduction.

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