# Open-domain medical Question Answering on MedQA US

Source: [Open-domain medical Question Answering on MedQA US](<https://www.sota2.com/research/sota/open-domain-medical-question-answering-on-medqa-us>)

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

Data updated: 2026-02-26T05:30:33.689Z

Evaluation of model performance on the MedQA US dataset for Open-domain medical Question Answering, measured using 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 | Open-domain medical Question Answering |
| Dataset (including any stated split) | MedQA US |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/open-domain-medical-question-answering-on-medqa-us.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| URCA | 85.9 | Not recorded | 68fa78e41e209131cea7b089 |
| GraphRAG | 84.5 | Not recorded | 68fa78e41e209131cea7b089 |
| RAG | 82.3 | Not recorded | 68fa78e41e209131cea7b089 |
| No RAG | 72.1 | Not recorded | 68fa78e41e209131cea7b089 |

### URCA

Accuracy: 85.9. Result ID: 6995aba53badfaffe6aa350b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e41e209131cea7b089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78e41e209131cea7b089.md>)

Recorded evaluation configuration: {"LLM":"GPT-4"}. This record does not assert independent reproduction.

### GraphRAG

Accuracy: 84.5. Result ID: 6995aba53badfaffe6aa350a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e41e209131cea7b089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770d1e209131cea70c5a.md>)

Recorded evaluation configuration: {"LLM":"GPT-4"}. This record does not assert independent reproduction.

### RAG

Accuracy: 82.3. Result ID: 6995aba53badfaffe6aa3509.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e41e209131cea7b089.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"LLM":"GPT-4"}. This record does not assert independent reproduction.

### No RAG

Accuracy: 72.1. Result ID: 6995aba53badfaffe6aa3508.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e41e209131cea7b089.md>)

Recorded evaluation configuration: {"LLM":"GPT-4"}. This record does not assert independent reproduction.

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