# Disease Recognition on CDDMBench

Source: [Disease Recognition on CDDMBench](<https://www.sota2.com/research/sota/disease-recognition-on-cddmbench>)

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

Data updated: 2026-02-26T05:31:40.335Z

Evaluation of Disease Recognition performance on the CDDMBench dataset, measured by Accuracy.

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 | Disease Recognition |
| Dataset (including any stated split) | CDDMBench |
| 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/disease-recognition-on-cddmbench.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-VL-Chat-AG (7B) | 91.5 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen2.5-VL-3B-Instruct | 72.5 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen2.5-VL-3B-Instruct | 69.43 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen-VL-Chat-AG\* (7B) | 66.1 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen2.5-VL-3B-Instruct | 58.84 | Not recorded | 69608b6553fdd5c361744176 |
| Gpt-5-Nano | 33.7 | Not recorded | 69608b6553fdd5c361744176 |
| Gpt-5-Nano | 31.6 | Not recorded | 69608b6553fdd5c361744176 |
| Gpt-5-Nano | 29.8 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen-VL-Chat (7B) | 25.39 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen-VL-Chat (7B) | 24.49 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen-VL-Chat (7B) | 12.1 | Not recorded | 69608b6553fdd5c361744176 |
| Gpt-5-Nano | 11 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen2.5-VL-3B-Instruct | 6.96 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen-VL-Chat (7B) | 5 | Not recorded | 69608b6553fdd5c361744176 |
| Qwen2.5-VL-3B-Instruct | 4.84 | Not recorded | 69608b6553fdd5c361744176 |

### Qwen-VL-Chat-AG (7B)

Accuracy: 91.5. Result ID: 6997d9e95698665ec43229fd.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"SFT (Unfrozen encoder)"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B-Instruct

Accuracy: 72.5. Result ID: 6997d9e95698665ec4322a09.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"Reasoning-Enhanced GRPO"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B-Instruct

Accuracy: 69.43. Result ID: 6997d9e95698665ec4322a08.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"GRPO"}. This record does not assert independent reproduction.

### Qwen-VL-Chat-AG\* (7B)

Accuracy: 66.1. Result ID: 6997d9e95698665ec43229fc.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"SFT (Frozen encoder)"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B-Instruct

Accuracy: 58.84. Result ID: 6997d9e95698665ec4322a07.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"SFT"}. This record does not assert independent reproduction.

### Gpt-5-Nano

Accuracy: 33.7. Result ID: 6997d9e95698665ec4322a04.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff9a53fdd5c36173e1c0.md>)

Recorded evaluation configuration: {"Method":"+Judge"}. This record does not assert independent reproduction.

### Gpt-5-Nano

Accuracy: 31.6. Result ID: 6997d9e95698665ec4322a02.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff9a53fdd5c36173e1c0.md>)

Recorded evaluation configuration: {"Method":"Expl. Caption"}. This record does not assert independent reproduction.

### Gpt-5-Nano

Accuracy: 29.8. Result ID: 6997d9e95698665ec4322a03.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff9a53fdd5c36173e1c0.md>)

Recorded evaluation configuration: {"Method":"+Few-shot"}. This record does not assert independent reproduction.

### Qwen-VL-Chat (7B)

Accuracy: 25.39. Result ID: 6997d9e95698665ec4322a00.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"+Judge"}. This record does not assert independent reproduction.

### Qwen-VL-Chat (7B)

Accuracy: 24.49. Result ID: 6997d9e95698665ec43229ff.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"+Few-shot"}. This record does not assert independent reproduction.

### Qwen-VL-Chat (7B)

Accuracy: 12.1. Result ID: 6997d9e95698665ec43229fe.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"Expl. Caption"}. This record does not assert independent reproduction.

### Gpt-5-Nano

Accuracy: 11. Result ID: 6997d9e95698665ec4322a01.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff9a53fdd5c36173e1c0.md>)

Recorded evaluation configuration: {"Method":"Zero-shot"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B-Instruct

Accuracy: 6.96. Result ID: 6997d9e95698665ec4322a06.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"Few-shot"}. This record does not assert independent reproduction.

### Qwen-VL-Chat (7B)

Accuracy: 5. Result ID: 6997d9e95698665ec43229fb.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"Zero-shot"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B-Instruct

Accuracy: 4.84. Result ID: 6997d9e95698665ec4322a05.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6553fdd5c361744176.md>)

Recorded evaluation configuration: {"Method":"Zero-shot"}. This record does not assert independent reproduction.

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