# Multi-disease IOS diagnosis on IOSVQA (test)

Source: [Multi-disease IOS diagnosis on IOSVQA (test)](<https://www.sota2.com/research/sota/multi-disease-ios-diagnosis-on-iosvqa-test>)

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

Data updated: 2026-03-18T09:23:24.787Z

Evaluation of multi-disease diagnosis performance on the test split of the IOSVQA dataset, measured using metrics such as Accuracy, F1 score, Precision, Recall, and PR.

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 | Multi-disease IOS diagnosis |
| Dataset (including any stated split) | IOSVQA (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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/multi-disease-ios-diagnosis-on-iosvqa-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/multi-disease-ios-diagnosis-on-iosvqa-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/multi-disease-ios-diagnosis-on-iosvqa-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/multi-disease-ios-diagnosis-on-iosvqa-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [PR AUC](<https://www.sota2.com/research/sota/multi-disease-ios-diagnosis-on-iosvqa-test.md?metric=PR%20AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IOSVLM | 77.23 | Not recorded | 69ba31b70636e5bf4afc0aad |
| Gemini 3 Pro | 67.65 | Not recorded | 69ba31b70636e5bf4afc0aad |
| GPT-5 | 62.26 | Not recorded | 69ba31b70636e5bf4afc0aad |
| HuluMed-7B | 61.21 | Not recorded | 69ba31b70636e5bf4afc0aad |
| HuatuoGPT-V-7B | 59.26 | Not recorded | 69ba31b70636e5bf4afc0aad |
| Qwen3VL-8B | 57.88 | Not recorded | 69ba31b70636e5bf4afc0aad |
| InternVL3.5-8B | 56.23 | Not recorded | 69ba31b70636e5bf4afc0aad |
| HuluMed-14B | 53.72 | Not recorded | 69ba31b70636e5bf4afc0aad |
| MedGemma-1.5 | 52.21 | Not recorded | 69ba31b70636e5bf4afc0aad |
| PointLLM-7B | 43.03 | Not recorded | 69ba31b70636e5bf4afc0aad |
| InternVL3.5-14B | 35.68 | Not recorded | 69ba31b70636e5bf4afc0aad |
| PointLLM-13B | 34.57 | Not recorded | 69ba31b70636e5bf4afc0aad |
| ShapeLLM-7B | 30.27 | Not recorded | 69ba31b70636e5bf4afc0aad |
| ShapeLLM-13B | 26.13 | Not recorded | 69ba31b70636e5bf4afc0aad |

### IOSVLM

Accuracy: 77.23. Result ID: 69ba6f0b47f34ce924a4abf5.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

Recorded evaluation configuration: {"Input":"3D Point Cloud"}. This record does not assert independent reproduction.

### Gemini 3 Pro

Accuracy: 67.65. Result ID: 69ba6f0b47f34ce924a4abe9.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### GPT-5

Accuracy: 62.26. Result ID: 69ba6f0b47f34ce924a4abe8.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### HuluMed-7B

Accuracy: 61.21. Result ID: 69ba6f0b47f34ce924a4abef.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfd1e209131cea8bb56.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### HuatuoGPT-V-7B

Accuracy: 59.26. Result ID: 69ba6f0b47f34ce924a4abee.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### Qwen3VL-8B

Accuracy: 57.88. Result ID: 69ba6f0b47f34ce924a4abea.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

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

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### InternVL3.5-8B

Accuracy: 56.23. Result ID: 69ba6f0b47f34ce924a4abeb.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### HuluMed-14B

Accuracy: 53.72. Result ID: 69ba6f0b47f34ce924a4abf0.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfd1e209131cea8bb56.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### MedGemma-1.5

Accuracy: 52.21. Result ID: 69ba6f0b47f34ce924a4abed.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

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

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### PointLLM-7B

Accuracy: 43.03. Result ID: 69ba6f0b47f34ce924a4abf1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b44.md>)

[Implementation](<https://github.com/OpenRobotLab/PointLLM>)

Recorded evaluation configuration: {"Input":"3D Point Cloud"}. This record does not assert independent reproduction.

### InternVL3.5-14B

Accuracy: 35.68. Result ID: 69ba6f0b47f34ce924a4abec.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"Input":"Multi-View Images"}. This record does not assert independent reproduction.

### PointLLM-13B

Accuracy: 34.57. Result ID: 69ba6f0b47f34ce924a4abf2.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b44.md>)

[Implementation](<https://github.com/OpenRobotLab/PointLLM>)

Recorded evaluation configuration: {"Input":"3D Point Cloud"}. This record does not assert independent reproduction.

### ShapeLLM-7B

Accuracy: 30.27. Result ID: 69ba6f0b47f34ce924a4abf3.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740c1e209131cea5f73a.md>)

[Implementation](<https://qizekun.github.io/ShapeLLM>)

Recorded evaluation configuration: {"Input":"3D Point Cloud"}. This record does not assert independent reproduction.

### ShapeLLM-13B

Accuracy: 26.13. Result ID: 69ba6f0b47f34ce924a4abf4.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b70636e5bf4afc0aad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740c1e209131cea5f73a.md>)

[Implementation](<https://qizekun.github.io/ShapeLLM>)

Recorded evaluation configuration: {"Input":"3D Point Cloud"}. This record does not assert independent reproduction.

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