# Medical Question Answering on MedQuAD-style Complete Benchmark

Source: [Medical Question Answering on MedQuAD-style Complete Benchmark](<https://www.sota2.com/research/sota/medical-question-answering-on-medquad-style-complete-benchmark>)

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

Data updated: 2026-02-26T05:52:28.982Z

Evaluation of model performance on the complete MedQuAD-style benchmark dataset for Medical Question Answering, reporting specific MedQuAD-style results and completion rates.

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) | MedQuAD-style Complete Benchmark |
| Metric | MedQuAD Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [MedQuAD Score](<https://www.sota2.com/research/sota/medical-question-answering-on-medquad-style-complete-benchmark.md?metric=MedQuAD%20Score>): Higher is better; unit: PERCENT.

- [Completion Rate](<https://www.sota2.com/research/sota/medical-question-answering-on-medquad-style-complete-benchmark.md?metric=Completion%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MedQuAD Score | Result date | Report paper |
| --- | --- | --- | --- |
| Med-Gemini | 91.1 | Not recorded | 69802f68a8b01e76cc8e14d8 |
| Med-PaLM 2 | 86.5 | Not recorded | 69802f68a8b01e76cc8e14d8 |
| Knowledge-Embed Model | 82.92 | Not recorded | 69802f68a8b01e76cc8e14d8 |
| GPT-4 | 71.07 | Not recorded | 69802f68a8b01e76cc8e14d8 |
| Med-PaLM (original) | 67.6 | Not recorded | 69802f68a8b01e76cc8e14d8 |

### Med-Gemini

MedQuAD Score: 91.1. Result ID: 699615ec5698665ec4558346.

[Reporting paper](<https://www.sota2.com/research/paper/69802f68a8b01e76cc8e14d8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Med-PaLM 2

MedQuAD Score: 86.5. Result ID: 699615ec5698665ec4558345.

[Reporting paper](<https://www.sota2.com/research/paper/69802f68a8b01e76cc8e14d8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Knowledge-Embed Model

MedQuAD Score: 82.92. Result ID: 699615ec5698665ec4558344.

[Reporting paper](<https://www.sota2.com/research/paper/69802f68a8b01e76cc8e14d8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4

MedQuAD Score: 71.07. Result ID: 699615ec5698665ec4558343.

[Reporting paper](<https://www.sota2.com/research/paper/69802f68a8b01e76cc8e14d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f051e209131cea43487.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Med-PaLM (original)

MedQuAD Score: 67.6. Result ID: 699615ec5698665ec4558342.

[Reporting paper](<https://www.sota2.com/research/paper/69802f68a8b01e76cc8e14d8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e4c1e209131cea3f1c6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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