# Image Classification on HatefulMemes I (test)

Source: [Image Classification on HatefulMemes I (test)](<https://www.sota2.com/research/sota/image-classification-on-hatefulmemes-i-test>)

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

Data updated: 2026-02-26T06:00:21.054Z

Evaluation of model performance on the test split of the HatefulMemes I dataset for the Image Classification task, typically measured using ROC AUC.

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) | HatefulMemes I (test) |
| Metric | ROC AUC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [ROC AUC](<https://www.sota2.com/research/sota/image-classification-on-hatefulmemes-i-test.md?metric=ROC%20AUC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ROC AUC | Result date | Report paper |
| --- | --- | --- | --- |
| Pretrained FT SOTA | 0.791 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo | 0.7 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo | 0.686 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-9B | 0.635 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-9B | 0.627 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-9B | 0.57 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-3B | 0.563 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-3B | 0.537 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo-3B | 0.536 | Not recorded | 68fa6e031e209131cea3d674 |
| Flamingo | 0.464 | Not recorded | 68fa6e031e209131cea3d674 |
| Zero/Few shot SOTA | 0.407 | Not recorded | 68fa6e031e209131cea3d674 |

### Pretrained FT SOTA

ROC AUC: 0.791. Result ID: 698ff4343a6c314849fd086b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":true,"Shot":"9K"}. This record does not assert independent reproduction.

### Flamingo

ROC AUC: 0.7. Result ID: 698ff4343a6c314849fd086a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":32}. This record does not assert independent reproduction.

### Flamingo

ROC AUC: 0.686. Result ID: 698ff4343a6c314849fd0869.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":4}. This record does not assert independent reproduction.

### Flamingo-9B

ROC AUC: 0.635. Result ID: 698ff4343a6c314849fd0867.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":32}. This record does not assert independent reproduction.

### Flamingo-9B

ROC AUC: 0.627. Result ID: 698ff4343a6c314849fd0866.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":4}. This record does not assert independent reproduction.

### Flamingo-9B

ROC AUC: 0.57. Result ID: 698ff4343a6c314849fd0865.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":0}. This record does not assert independent reproduction.

### Flamingo-3B

ROC AUC: 0.563. Result ID: 698ff4343a6c314849fd0864.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":32}. This record does not assert independent reproduction.

### Flamingo-3B

ROC AUC: 0.537. Result ID: 698ff4343a6c314849fd0862.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":0}. This record does not assert independent reproduction.

### Flamingo-3B

ROC AUC: 0.536. Result ID: 698ff4343a6c314849fd0863.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":4}. This record does not assert independent reproduction.

### Flamingo

ROC AUC: 0.464. Result ID: 698ff4343a6c314849fd0868.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":0}. This record does not assert independent reproduction.

### Zero/Few shot SOTA

ROC AUC: 0.407. Result ID: 698ff4343a6c314849fd0861.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d674.md>)

Recorded evaluation configuration: {"FT":false,"Shot":0}. This record does not assert independent reproduction.

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