# Image Classification on CIFAR-100 (Communication and Latency Evaluation)

Source: [Image Classification on CIFAR-100 (Communication and Latency Evaluation)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-communication-and-latency-evaluation>)

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

Data updated: 2026-02-26T05:39:34.898Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, reporting standard Top-1 Accuracy alongside communication overhead and inference latency.

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) | CIFAR-100 |
| Metric | Communication (GB) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [Communication (GB)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-communication-and-latency-evaluation.md?metric=Communication%20(GB)>): Lower is better; unit: SIZE.

- [Latency (s)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-communication-and-latency-evaluation.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-communication-and-latency-evaluation.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Communication (GB) | Result date | Report paper |
| --- | --- | --- | --- |
| UFO | 0.525 | Not recorded | 699d30996017c4460ffab4fd |
| CrypTFlow2 | 0.681 | Not recorded | 699d30996017c4460ffab4fd |
| Delphi | 6.5 | Not recorded | 699d30996017c4460ffab4fd |
| Gazelle | 8.9 | Not recorded | 699d30996017c4460ffab4fd |

### UFO

Communication (GB): 0.525. Result ID: 699e2a1a5698665ec4e503ea.

[Reporting paper](<https://www.sota2.com/research/paper/699d30996017c4460ffab4fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30996017c4460ffab4fd.md>)

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

### CrypTFlow2

Communication (GB): 0.681. Result ID: 699e2a1a5698665ec4e503e9.

[Reporting paper](<https://www.sota2.com/research/paper/699d30996017c4460ffab4fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687f1e209131cea1c5c9.md>)

Recorded evaluation configuration: {"HE protocol implementation for linear layers":true}. This record does not assert independent reproduction.

### Delphi

Communication (GB): 6.5. Result ID: 699e2a1a5698665ec4e503e8.

[Reporting paper](<https://www.sota2.com/research/paper/699d30996017c4460ffab4fd.md>)

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

### Gazelle

Communication (GB): 8.9. Result ID: 699e2a1a5698665ec4e503e7.

[Reporting paper](<https://www.sota2.com/research/paper/699d30996017c4460ffab4fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f51e209131cea01daa.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.
