# Comparison-QA on Heartcare-BenchC S-S, Irr.

Source: [Comparison-QA on Heartcare-BenchC S-S, Irr.](<https://www.sota2.com/research/sota/comparison-qa-on-heartcare-benchc-s-s-irr>)

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

Data updated: 2026-04-08T07:08:26.533Z

Evaluation of Comparison Question Answering performance on the Heartcare-BenchC S-S, Irr. dataset, reporting 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 | Comparison-QA |
| Dataset (including any stated split) | Heartcare-BenchC S-S, Irr. |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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/comparison-qa-on-heartcare-benchc-s-s-irr.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HeartcareGPT-7B | 75.87 | Not recorded | 68fa793f1e209131cea7cd9b |
| HeartcareGPT-3.8B | 67.47 | Not recorded | 68fa793f1e209131cea7cd9b |
| LLaVA-1.5-7B | 56.24 | Not recorded | 68fa793f1e209131cea7cd9b |
| GPT5 | 49.18 | Not recorded | 68fa793f1e209131cea7cd9b |
| MiniCPM-V2.6-8B | 48.13 | Not recorded | 68fa793f1e209131cea7cd9b |
| Qwen2.5-VL-7B | 47.26 | Not recorded | 68fa793f1e209131cea7cd9b |
| InternVL-2.5-8B | 45.13 | Not recorded | 68fa793f1e209131cea7cd9b |
| Lingshu-7B | 45.01 | Not recorded | 68fa793f1e209131cea7cd9b |
| Claude-3.5 | 43.96 | Not recorded | 68fa793f1e209131cea7cd9b |
| MedVLM-R1-2B | 39.33 | Not recorded | 68fa793f1e209131cea7cd9b |
| Gemma-3-4B | 38.53 | Not recorded | 68fa793f1e209131cea7cd9b |
| LLaVA-Med-7B | 34.82 | Not recorded | 68fa793f1e209131cea7cd9b |

### HeartcareGPT-7B

Accuracy: 75.87. Result ID: 69d5fee247f34ce924be17b4.

[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-3.8B

Accuracy: 67.47. Result ID: 69d5fee247f34ce924be17b3.

[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.

### LLaVA-1.5-7B

Accuracy: 56.24. Result ID: 69d5fee247f34ce924be17a9.

[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.

### GPT5

Accuracy: 49.18. Result ID: 69d5fee247f34ce924be17af.

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

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

### MiniCPM-V2.6-8B

Accuracy: 48.13. Result ID: 69d5fee247f34ce924be17ac.

[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.

### Qwen2.5-VL-7B

Accuracy: 47.26. Result ID: 69d5fee247f34ce924be17aa.

[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.

### InternVL-2.5-8B

Accuracy: 45.13. Result ID: 69d5fee247f34ce924be17ab.

[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.

### Lingshu-7B

Accuracy: 45.01. Result ID: 69d5fee247f34ce924be17b0.

[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.

### Claude-3.5

Accuracy: 43.96. Result ID: 69d5fee247f34ce924be17ae.

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

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

### MedVLM-R1-2B

Accuracy: 39.33. Result ID: 69d5fee247f34ce924be17b2.

[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.

### Gemma-3-4B

Accuracy: 38.53. Result ID: 69d5fee247f34ce924be17ad.

[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.

### LLaVA-Med-7B

Accuracy: 34.82. Result ID: 69d5fee247f34ce924be17b1.

[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.

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