# Medical Question Answering on MedQA-USMLE (Accuracy, F1, Precision, Recall)

Source: [Medical Question Answering on MedQA-USMLE (Accuracy, F1, Precision, Recall)](<https://www.sota2.com/research/sota/medical-question-answering-on-medqa-usmle-accuracy-f1-precision-recall>)

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

Data updated: 2026-06-04T09:22:38.320Z

Evaluation of model performance on the MedQA USMLE dataset using Accuracy, F1-score, Precision, and Recall.

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) | MedQA-USMLE |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-medqa-usmle-accuracy-f1-precision-recall.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/medical-question-answering-on-medqa-usmle-accuracy-f1-precision-recall.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/medical-question-answering-on-medqa-usmle-accuracy-f1-precision-recall.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/medical-question-answering-on-medqa-usmle-accuracy-f1-precision-recall.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-2.5-7B | 56.95 | Not recorded | 6a2106a0c10484bac23f0253 |
| Llama-3.1-Aloe-Beta-8B | 56.25 | Not recorded | 6a2106a0c10484bac23f0253 |
| Llama-3.1-8B | 53.26 | Not recorded | 6a2106a0c10484bac23f0253 |
| Llama-3-Med42-8B | 51.99 | Not recorded | 6a2106a0c10484bac23f0253 |
| Mistral-7B-Instruct-v0.3 | 47.09 | Not recorded | 6a2106a0c10484bac23f0253 |

### Qwen-2.5-7B

Accuracy: 56.95. Result ID: 6a2143d2fbc373592c1d21e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a0c10484bac23f0253.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Data Format":"plaintext"}. This record does not assert independent reproduction.

### Llama-3.1-Aloe-Beta-8B

Accuracy: 56.25. Result ID: 6a2143d2fbc373592c1d21e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a0c10484bac23f0253.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ea1e209131cea7b317.md>)

Recorded evaluation configuration: {"Data Format":"plaintext"}. This record does not assert independent reproduction.

### Llama-3.1-8B

Accuracy: 53.26. Result ID: 6a2143d2fbc373592c1d21e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a0c10484bac23f0253.md>)

Recorded evaluation configuration: {"Data Format":"plaintext"}. This record does not assert independent reproduction.

### Llama-3-Med42-8B

Accuracy: 51.99. Result ID: 6a2143d2fbc373592c1d21e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a0c10484bac23f0253.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74741e209131cea61e3d.md>)

Recorded evaluation configuration: {"Data Format":"plaintext"}. This record does not assert independent reproduction.

### Mistral-7B-Instruct-v0.3

Accuracy: 47.09. Result ID: 6a2143d2fbc373592c1d21e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a0c10484bac23f0253.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Data Format":"plaintext"}. This record does not assert independent reproduction.

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