# Closed-QA on Heartcare-BenchI

Source: [Closed-QA on Heartcare-BenchI](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi>)

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

Data updated: 2026-04-08T07:08:26.402Z

Evaluation of Closed-Question Answering performance on the Heartcare-BenchI dataset, reporting scores across Diagnosis, Waveform, Rhythm, and miscellaneous categories.

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 | Closed-QA |
| Dataset (including any stated split) | Heartcare-BenchI |
| Metric | Diagnosis 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

- [Diagnosis Accuracy](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi.md?metric=Diagnosis%20Accuracy>): Higher is better; unit: PERCENT.

- [Waveform Accuracy](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi.md?metric=Waveform%20Accuracy>): Higher is better; unit: PERCENT.

- [Rhythm Accuracy](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi.md?metric=Rhythm%20Accuracy>): Higher is better; unit: PERCENT.

- [Miscellaneous Accuracy](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi.md?metric=Miscellaneous%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/closed-qa-on-heartcare-benchi.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Diagnosis Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HeartcareGPT-3.8B | 87.85 | Not recorded | 68fa793f1e209131cea7cd9b |
| HeartcareGPT-7B | 62.71 | Not recorded | 68fa793f1e209131cea7cd9b |
| Yi-VL-6B | 59.55 | Not recorded | 68fa793f1e209131cea7cd9b |
| Lingshu-7B | 47.96 | Not recorded | 68fa793f1e209131cea7cd9b |
| GPT5 | 41.42 | Not recorded | 68fa793f1e209131cea7cd9b |
| Gemma-3-4B | 38.73 | Not recorded | 68fa793f1e209131cea7cd9b |
| Qwen2.5-VL-7B | 35.84 | Not recorded | 68fa793f1e209131cea7cd9b |
| Claude-3.5 | 30.58 | Not recorded | 68fa793f1e209131cea7cd9b |
| InternVL-2.5-8B | 25.86 | Not recorded | 68fa793f1e209131cea7cd9b |
| LLaVA-Med-7B | 25.11 | Not recorded | 68fa793f1e209131cea7cd9b |
| MiniCPM-V2.6-8B | 23.71 | Not recorded | 68fa793f1e209131cea7cd9b |
| HealthGPT-M3-3.8B | 15.35 | Not recorded | 68fa793f1e209131cea7cd9b |
| LLaVA-1.5-7B | 15.15 | Not recorded | 68fa793f1e209131cea7cd9b |
| MedVLM-R1-2B | 14.08 | Not recorded | 68fa793f1e209131cea7cd9b |

### HeartcareGPT-3.8B

Diagnosis Accuracy: 87.85. Result ID: 69d5fee247f34ce924be177f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

### HeartcareGPT-7B

Diagnosis Accuracy: 62.71. Result ID: 69d5fee247f34ce924be1780.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

### Yi-VL-6B

Diagnosis Accuracy: 59.55. Result ID: 69d5fee247f34ce924be1776.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a71e209131cea6e366.md>)

[Implementation](<https://github.com/01-ai/Yi>)

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### Lingshu-7B

Diagnosis Accuracy: 47.96. Result ID: 69d5fee247f34ce924be177b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795a1e209131cea7d387.md>)

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

### GPT5

Diagnosis Accuracy: 41.42. Result ID: 69d5fee247f34ce924be177a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### Gemma-3-4B

Diagnosis Accuracy: 38.73. Result ID: 69d5fee247f34ce924be1778.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

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

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Diagnosis Accuracy: 35.84. Result ID: 69d5fee247f34ce924be1774.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

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

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### Claude-3.5

Diagnosis Accuracy: 30.58. Result ID: 69d5fee247f34ce924be1779.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### InternVL-2.5-8B

Diagnosis Accuracy: 25.86. Result ID: 69d5fee247f34ce924be1775.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bab1e209131cea89c7f.md>)

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

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### LLaVA-Med-7B

Diagnosis Accuracy: 25.11. Result ID: 69d5fee247f34ce924be177c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea46356.md>)

[Implementation](<https://aka.ms/llava-med>)

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

### MiniCPM-V2.6-8B

Diagnosis Accuracy: 23.71. Result ID: 69d5fee247f34ce924be1777.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3ab.md>)

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### HealthGPT-M3-3.8B

Diagnosis Accuracy: 15.35. Result ID: 69d5fee247f34ce924be177e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77201e209131cea713ef.md>)

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

### LLaVA-1.5-7B

Diagnosis Accuracy: 15.15. Result ID: 69d5fee247f34ce924be1773.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Type":"Generalist Models"}. This record does not assert independent reproduction.

### MedVLM-R1-2B

Diagnosis Accuracy: 14.08. Result ID: 69d5fee247f34ce924be177d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa793f1e209131cea7cd9b.md>)

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

Recorded evaluation configuration: {"Model Type":"Medical Models"}. This record does not assert independent reproduction.

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