# Biomedical Question Answering on PubMedQA (test)

Source: [Biomedical Question Answering on PubMedQA (test)](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa-test>)

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

Data updated: 2026-04-01T06:41:55.712Z

Evaluation of model performance on the test split of the PubMedQA dataset for Biomedical Question Answering, reporting CUS, ZTI, and ECE 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 | Biomedical Question Answering |
| Dataset (including any stated split) | PubMedQA (test) |
| Metric | CUS |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [CUS](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa-test.md?metric=CUS>): Lower is better; unit: SCALAR.

- [ZTI](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa-test.md?metric=ZTI>): Lower is better; unit: SCALAR.

- [ECE](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa-test.md?metric=ECE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | CUS | Result date | Report paper |
| --- | --- | --- | --- |
| MedBayes-Lite | 0.254 | Not recorded | 691ff20cd6b0dd334292e6ac |
| GPT-2 | 0.376 | Not recorded | 691ff20cd6b0dd334292e6ac |

### MedBayes-Lite

CUS: 0.254. Result ID: 69ccbd4447f34ce924b5cba4.

[Reporting paper](<https://www.sota2.com/research/paper/691ff20cd6b0dd334292e6ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ff20cd6b0dd334292e6ac.md>)

Recorded evaluation configuration: {"Train dataset":"MIMIC-III"}. This record does not assert independent reproduction.

### GPT-2

CUS: 0.376. Result ID: 69ccbd4447f34ce924b5cba3.

[Reporting paper](<https://www.sota2.com/research/paper/691ff20cd6b0dd334292e6ac.md>)

Recorded evaluation configuration: {"Train dataset":"MIMIC-III"}. This record does not assert independent reproduction.

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