# Medical Question Answering on AfriMed

Source: [Medical Question Answering on AfriMed](<https://www.sota2.com/research/sota/medical-question-answering-on-afrimed>)

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

Data updated: 2026-04-08T07:16:59.487Z

Evaluation of model performance on the AfriMed dataset for Medical Question Answering, reporting Accuracy scores.

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 | Medical Question Answering |
| Dataset (including any stated split) | AfriMed |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/medical-question-answering-on-afrimed.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek R1 | 92 | Not recorded | 68fa79ff1e209131cea808a4 |
| MedGemma 27B | 84 | Not recorded | 68fa79ff1e209131cea808a4 |
| Gemini 2.5 Flash | 84 | Not recorded | 68fa79ff1e209131cea808a4 |
| Gemini 2.5 Pro | 84 | Not recorded | 68fa79ff1e209131cea808a4 |
| o3 | 84 | Not recorded | 68fa79ff1e209131cea808a4 |
| GPT-4o | 80 | Not recorded | 68fa79ff1e209131cea808a4 |
| Gemma 3 27B | 72 | Not recorded | 68fa79ff1e209131cea808a4 |
| MedGemma 4B | 52 | Not recorded | 68fa79ff1e209131cea808a4 |
| Gemma 3 4B | 48 | Not recorded | 68fa79ff1e209131cea808a4 |

### DeepSeek R1

Accuracy: 92. Result ID: 69d5ff9747f34ce924be1a48.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Size category":"Large Models"}. This record does not assert independent reproduction.

### MedGemma 27B

Accuracy: 84. Result ID: 69d5ff9747f34ce924be1a46.

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

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

Recorded evaluation configuration: {"Size category":"Small Models","test-time scaling":true}. This record does not assert independent reproduction.

### Gemini 2.5 Flash

Accuracy: 84. Result ID: 69d5ff9747f34ce924be1a49.

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

Recorded evaluation configuration: {"Size category":"Large Models"}. This record does not assert independent reproduction.

### Gemini 2.5 Pro

Accuracy: 84. Result ID: 69d5ff9747f34ce924be1a4a.

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

Recorded evaluation configuration: {"Size category":"Large Models"}. This record does not assert independent reproduction.

### o3

Accuracy: 84. Result ID: 69d5ff9747f34ce924be1a4c.

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

Recorded evaluation configuration: {"Size category":"Large Models"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 80. Result ID: 69d5ff9747f34ce924be1a4b.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Size category":"Large Models"}. This record does not assert independent reproduction.

### Gemma 3 27B

Accuracy: 72. Result ID: 69d5ff9747f34ce924be1a47.

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

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

Recorded evaluation configuration: {"Size category":"Small Models"}. This record does not assert independent reproduction.

### MedGemma 4B

Accuracy: 52. Result ID: 69d5ff9747f34ce924be1a44.

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

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

Recorded evaluation configuration: {"Size category":"Small Models"}. This record does not assert independent reproduction.

### Gemma 3 4B

Accuracy: 48. Result ID: 69d5ff9747f34ce924be1a45.

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

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

Recorded evaluation configuration: {"Size category":"Small Models"}. This record does not assert independent reproduction.

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