# Image Modeling on ImageNet 32x32 (val)

Source: [Image Modeling on ImageNet 32x32 (val)](<https://www.sota2.com/research/sota/image-modeling-on-imagenet-32x32-val>)

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

Data updated: 2026-02-26T05:53:17.272Z

Evaluation of Image Modeling performance (density estimation or likelihood) on the validation split of the ImageNet 32x32 dataset, typically measured using Negative Log-Likelihood (NLL).

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 Modeling |
| Dataset (including any stated split) | ImageNet 32x32 (val) |
| Metric | NLL (bits/dim) |
| Unit | OTHER |
| 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

- [NLL (bits/dim)](<https://www.sota2.com/research/sota/image-modeling-on-imagenet-32x32-val.md?metric=NLL%20(bits%2Fdim)>): Lower is better; unit: OTHER.

## Recorded results

| Method | NLL (bits/dim) | Result date | Report paper |
| --- | --- | --- | --- |
| PixelRNN | 3.86 | Not recorded | 68fa62b81e209131ce9fad7e |
| PixelRNN | 3.86 | Not recorded | 68fa63351e209131ce9fd6b3 |
| Real NVP | 4.28 | Not recorded | 68fa63351e209131ce9fd6b3 |

### PixelRNN

NLL (bits/dim): 3.86. Result ID: 698be0b4ecace47ef5598b98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62b81e209131ce9fad7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62b81e209131ce9fad7e.md>)

Recorded evaluation configuration: {"Resolution":"32x32","Data Augmentation":false}. This record does not assert independent reproduction.

### PixelRNN

NLL (bits/dim): 3.86. Result ID: 698c701f37894ef7d9ce6362.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63351e209131ce9fd6b3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62b81e209131ce9fad7e.md>)

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

### Real NVP

NLL (bits/dim): 4.28. Result ID: 698c701f37894ef7d9ce6363.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63351e209131ce9fd6b3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63351e209131ce9fd6b3.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.