# Diagnostic Classification on derm7pt Melanoma vs. Atypical Nevus (test)

Source: [Diagnostic Classification on derm7pt Melanoma vs. Atypical Nevus (test)](<https://www.sota2.com/research/sota/diagnostic-classification-on-derm7pt-melanoma-vs-atypical-nevus-test>)

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

Data updated: 2026-06-19T07:43:20.052Z

Evaluation of Diagnostic Classification performance on the test split of the derm7pt dataset, specifically focusing on distinguishing Melanoma from Atypical Nevus, measured using Accuracy (ACC), F1 score, and Youden's Index.

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 | Diagnostic Classification |
| Dataset (including any stated split) | derm7pt Melanoma vs. Atypical Nevus (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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/diagnostic-classification-on-derm7pt-melanoma-vs-atypical-nevus-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/diagnostic-classification-on-derm7pt-melanoma-vs-atypical-nevus-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Youden's Index](<https://www.sota2.com/research/sota/diagnostic-classification-on-derm7pt-melanoma-vs-atypical-nevus-test.md?metric=Youden%27s%20Index>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CARE | 77.6 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemini-3-Pro | 74.1 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Blind-CARE | 73.9 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemini-3-Flash (Self-Check 3x) | 71.9 | Not recorded | 69a125102d603e6de3e3c4e8 |
| GLM-4.6V-Flash | 71.8 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemini-3-Flash (Self-Check 2x) | 70.1 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Qwen3-VL-32B | 69.8 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemini-3-Flash (Majority-Vote 3x) | 68.6 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemini-3-Flash (Baseline) | 66.5 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Qwen3-VL-8B | 66.1 | Not recorded | 69a125102d603e6de3e3c4e8 |
| SigLIP2 | 61.1 | Not recorded | 69a125102d603e6de3e3c4e8 |
| BiomedCLIP | 60.7 | Not recorded | 69a125102d603e6de3e3c4e8 |
| InternVL3-14B | 54.9 | Not recorded | 69a125102d603e6de3e3c4e8 |
| MedVLM-R1 | 50.5 | Not recorded | 69a125102d603e6de3e3c4e8 |
| Gemma-3-12B | 49.9 | Not recorded | 69a125102d603e6de3e3c4e8 |

### CARE

Accuracy: 77.6. Result ID: 6a34f1defbc373592c31f548.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"CARE"}. This record does not assert independent reproduction.

### Gemini-3-Pro

Accuracy: 74.1. Result ID: 6a34f1defbc373592c31f549.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

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

### Blind-CARE

Accuracy: 73.9. Result ID: 6a34f1defbc373592c31f547.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"Blind-CARE","Access to original image":"false"}. This record does not assert independent reproduction.

### Gemini-3-Flash (Self-Check 3x)

Accuracy: 71.9. Result ID: 6a34f1defbc373592c31f545.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bff1e209131cea8bc97.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"Self-Check","Number of passes":"3x","Multi-pass self-revision":"true"}. This record does not assert independent reproduction.

### GLM-4.6V-Flash

Accuracy: 71.8. Result ID: 6a34f1defbc373592c31f542.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aaf1e209131cea849ba.md>)

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

### Gemini-3-Flash (Self-Check 2x)

Accuracy: 70.1. Result ID: 6a34f1defbc373592c31f544.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bff1e209131cea8bc97.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"Self-Check","Number of passes":"2x","Multi-pass self-revision":"true"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

Accuracy: 69.8. Result ID: 6a34f1defbc373592c31f541.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

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

### Gemini-3-Flash (Majority-Vote 3x)

Accuracy: 68.6. Result ID: 6a34f1defbc373592c31f546.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c21e209131cea69c8b.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"Majority-Vote","Number of sampling":"3x","Independent sampling with majority aggregation":"true"}. This record does not assert independent reproduction.

### Gemini-3-Flash (Baseline)

Accuracy: 66.5. Result ID: 6a34f1defbc373592c31f543.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-3-Flash","Strategy":"Baseline"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Accuracy: 66.1. Result ID: 6a34f1defbc373592c31f540.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction.

### SigLIP2

Accuracy: 61.1. Result ID: 6a34f1defbc373592c31f53b.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770a1e209131cea70ad4.md>)

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

### BiomedCLIP

Accuracy: 60.7. Result ID: 6a34f1defbc373592c31f53c.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

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

### InternVL3-14B

Accuracy: 54.9. Result ID: 6a34f1defbc373592c31f53e.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Parameters":"14B"}. This record does not assert independent reproduction.

### MedVLM-R1

Accuracy: 50.5. Result ID: 6a34f1defbc373592c31f53d.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77831e209131cea73bcd.md>)

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

### Gemma-3-12B

Accuracy: 49.9. Result ID: 6a34f1defbc373592c31f53f.

[Reporting paper](<https://www.sota2.com/research/paper/69a125102d603e6de3e3c4e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Parameters":"12B"}. This record does not assert independent reproduction.

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