# Image Classification on ImageNet-1K (val) (NN, LP, and FT Accuracy)

Source: [Image Classification on ImageNet-1K (val) (NN, LP, and FT Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-nn-lp-and-ft-accuracy>)

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

Data updated: 2026-02-26T05:53:28.033Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting NN Accuracy, LP Accuracy, and FT Accuracy.

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-1K (val) |
| Metric | NN 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

- [NN Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-nn-lp-and-ft-accuracy.md?metric=NN%20Accuracy>): Higher is better; unit: PERCENT.

- [LP Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-nn-lp-and-ft-accuracy.md?metric=LP%20Accuracy>): Higher is better; unit: PERCENT.

- [FT Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-nn-lp-and-ft-accuracy.md?metric=FT%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NN Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DINO | 67.3 | Not recorded | 68fa757c1e209131cea68491 |
| DINO | 66 | Not recorded | 68fa757c1e209131cea68491 |
| MoCo | 61.9 | Not recorded | 68fa757c1e209131cea68491 |
| MoCo | 60.7 | Not recorded | 68fa757c1e209131cea68491 |
| SimCLR | 50.7 | Not recorded | 68fa757c1e209131cea68491 |
| SimCLR | 50.2 | Not recorded | 68fa757c1e209131cea68491 |

### DINO

NN Accuracy: 67.3. Result ID: 6993cbe53a6c314849189bb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"DINO","Optimized Acceleration Schedule":false,"Budget (M)":"2846"}. This record does not assert independent reproduction.

### DINO

NN Accuracy: 66. Result ID: 6993cbe53a6c314849189bb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"DINO","Optimized Acceleration Schedule":true,"Budget (M)":"1138"}. This record does not assert independent reproduction.

### MoCo

NN Accuracy: 61.9. Result ID: 6993cbe53a6c314849189bb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"MoCo","Optimized Acceleration Schedule":false,"Budget (M)":"6168"}. This record does not assert independent reproduction.

### MoCo

NN Accuracy: 60.7. Result ID: 6993cbe53a6c314849189bb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"MoCo","Optimized Acceleration Schedule":true,"Budget (M)":"1542"}. This record does not assert independent reproduction.

### SimCLR

NN Accuracy: 50.7. Result ID: 6993cbe53a6c314849189bb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"SimCLR","Optimized Acceleration Schedule":true,"Budget (M)":"922"}. This record does not assert independent reproduction.

### SimCLR

NN Accuracy: 50.2. Result ID: 6993cbe53a6c314849189bb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68491.md>)

Recorded evaluation configuration: {"Algorithm":"SimCLR","Optimized Acceleration Schedule":false,"Budget (M)":"3075"}. This record does not assert independent reproduction.

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