# Pigmentary abnormalities prediction on AREDS (test)

Source: [Pigmentary abnormalities prediction on AREDS (test)](<https://www.sota2.com/research/sota/pigmentary-abnormalities-prediction-on-areds-test>)

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

Data updated: 2026-04-29T08:23:14.550Z

Evaluation of models for predicting pigmentary abnormalities using the test split of the AREDS dataset, measured by Accuracy and F1-score.

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 | Pigmentary abnormalities prediction |
| Dataset (including any stated split) | AREDS (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/pigmentary-abnormalities-prediction-on-areds-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/pigmentary-abnormalities-prediction-on-areds-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| OcularChat | 84.9 | Not recorded | 69f1909855a3c32af89fbb04 |
| Qwen2.5-VL-72B | 78.5 | Not recorded | 69f1909855a3c32af89fbb04 |
| GPT-o1 | 77.6 | Not recorded | 69f1909855a3c32af89fbb04 |
| Qwen2.5-VL-32B | 74.9 | Not recorded | 69f1909855a3c32af89fbb04 |
| MedGemma-4B | 73.7 | Not recorded | 69f1909855a3c32af89fbb04 |
| Qwen2.5-VL-7B | 66.4 | Not recorded | 69f1909855a3c32af89fbb04 |
| Llama-3.2-90B-Vision | 64.5 | Not recorded | 69f1909855a3c32af89fbb04 |
| Llama-3.2-11B-Vision | 57 | Not recorded | 69f1909855a3c32af89fbb04 |

### OcularChat

Accuracy: 84.9. Result ID: 69f1bfdb47f34ce924d83551.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

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

### Qwen2.5-VL-72B

Accuracy: 78.5. Result ID: 69f1bfdb47f34ce924d8354c.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model size":"72B"}. This record does not assert independent reproduction.

### GPT-o1

Accuracy: 77.6. Result ID: 69f1bfdb47f34ce924d8354f.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76691e209131cea6ccaa.md>)

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

### Qwen2.5-VL-32B

Accuracy: 74.9. Result ID: 69f1bfdb47f34ce924d8354b.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model size":"32B"}. This record does not assert independent reproduction.

### MedGemma-4B

Accuracy: 73.7. Result ID: 69f1bfdb47f34ce924d83550.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

Recorded evaluation configuration: {"Model size":"4B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Accuracy: 66.4. Result ID: 69f1bfdb47f34ce924d8354a.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model size":"7B"}. This record does not assert independent reproduction.

### Llama-3.2-90B-Vision

Accuracy: 64.5. Result ID: 69f1bfdb47f34ce924d8354e.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

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

Recorded evaluation configuration: {"Model size":"90B"}. This record does not assert independent reproduction.

### Llama-3.2-11B-Vision

Accuracy: 57. Result ID: 69f1bfdb47f34ce924d8354d.

[Reporting paper](<https://www.sota2.com/research/paper/69f1909855a3c32af89fbb04.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

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

Recorded evaluation configuration: {"Model size":"11B"}. This record does not assert independent reproduction.

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