# Image Classification on ImageNet-1K (val) (Accuracy, Latency, and FLOPs)

Source: [Image Classification on ImageNet-1K (val) (Accuracy, Latency, and FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-accuracy-latency-and-flops>)

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

Data updated: 2026-02-26T05:48:28.359Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting standard accuracy, inference latency, and computational complexity (FLOPs).

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 | Latency (ms) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Latency (ms)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-accuracy-latency-and-flops.md?metric=Latency%20(ms)>): Lower is better; unit: TIME.

- [FLOPs (G)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-accuracy-latency-and-flops.md?metric=FLOPs%20(G)>): Lower is better; unit: SCALAR.

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

## Recorded results

| Method | Latency (ms) | Result date | Report paper |
| --- | --- | --- | --- |
| LTMP | 107 | Not recorded | 68fa70551e209131cea4a4ce |
| ToMe | 118 | Not recorded | 68fa70551e209131cea4a4ce |
| DeiT-S | 212 | Not recorded | 68fa70551e209131cea4a4ce |

### LTMP

Latency (ms): 107. Result ID: 699113213a6c314849057d0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4ce.md>)

[Implementation](<https://github.com/Mxbonn/ltmp>)

Recorded evaluation configuration: {"Hardware":"Google Pixel 7","Batch Size":1,"Optimization Framework":"PyTorch optimize\_for\_mobile","Average runs":"200"}. This record does not assert independent reproduction.

### ToMe

Latency (ms): 118. Result ID: 699113213a6c314849057d0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ea91e209131cea4130c.md>)

[Implementation](<http://github.com/facebookresearch/ToMe>)

Recorded evaluation configuration: {"Hardware":"Google Pixel 7","Batch Size":1,"Optimization Framework":"PyTorch optimize\_for\_mobile","Average runs":"200"}. This record does not assert independent reproduction.

### DeiT-S

Latency (ms): 212. Result ID: 699113213a6c314849057d0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69181e209131cea202b4.md>)

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

Recorded evaluation configuration: {"Hardware":"Google Pixel 7","Batch Size":1,"Optimization Framework":"PyTorch optimize\_for\_mobile","Average runs":"200"}. This record does not assert independent reproduction.

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