# Medical Question Answering on Medical QA Primary n=319 (test)

Source: [Medical Question Answering on Medical QA Primary n=319 (test)](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test>)

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

Data updated: 2026-05-22T07:56:06.893Z

Evaluation of model performance on the specific test split (n=319) of the Medical QA Primary dataset for Medical Question Answering, measured using UCCR, PAU, F1, and Action 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 | Medical Question Answering |
| Dataset (including any stated split) | Medical QA Primary n=319 (test) |
| Metric | UCCR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [UCCR](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test.md?metric=UCCR>): Higher is better; unit: PERCENT.

- [PAU](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test.md?metric=PAU>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Action Accuracy](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test.md?metric=Action%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | UCCR | Result date | Report paper |
| --- | --- | --- | --- |
| vanilla answer | 21.94 | Not recorded | 6a0fe325f984739ed6739e69 |
| citation only | 21.94 | Not recorded | 6a0fe325f984739ed6739e69 |
| binary answer / abstain | 0 | Not recorded | 6a0fe325f984739ed6739e69 |
| verifier only | 0 | Not recorded | 6a0fe325f984739ed6739e69 |
| speech-act-guided proxy | 0 | Not recorded | 6a0fe325f984739ed6739e69 |
| claim-selective + NLI relation | 0 | Not recorded | 6a0fe325f984739ed6739e69 |
| claim-selective + learned relation | 0 | Not recorded | 6a0fe325f984739ed6739e69 |
| claim-selective full | 0 | Not recorded | 6a0fe325f984739ed6739e69 |

### vanilla answer

UCCR: 21.94. Result ID: 6a100c12fbc373592c08c6c8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"binary-form"}. This record does not assert independent reproduction.

### citation only

UCCR: 21.94. Result ID: 6a100c12fbc373592c08c6cb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"binary-form"}. This record does not assert independent reproduction.

### binary answer / abstain

UCCR: 0. Result ID: 6a100c12fbc373592c08c6c9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"binary-form"}. This record does not assert independent reproduction.

### verifier only

UCCR: 0. Result ID: 6a100c12fbc373592c08c6ca.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"binary-form"}. This record does not assert independent reproduction.

### speech-act-guided proxy

UCCR: 0. Result ID: 6a100c12fbc373592c08c6cc.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"binary-form"}. This record does not assert independent reproduction.

### claim-selective + NLI relation

UCCR: 0. Result ID: 6a100c12fbc373592c08c6cd.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"native","relation\_type":"NLI"}. This record does not assert independent reproduction.

### claim-selective + learned relation

UCCR: 0. Result ID: 6a100c12fbc373592c08c6ce.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"native","relation\_type":"learned"}. This record does not assert independent reproduction.

### claim-selective full

UCCR: 0. Result ID: 6a100c12fbc373592c08c6cf.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69.md>)

Recorded evaluation configuration: {"action\_space":"native"}. This record does not assert independent reproduction.

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