# Biomedical Question Answering on PubMedQA

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

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

Data updated: 2026-06-02T06:25:17.906Z

Evaluation of model performance on the PubMedQA dataset for Biomedical Question Answering, reporting internal tracking scores such as Baseline Score, Best Score, and Final Score derived from accuracy counts (e.g., X/30).

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 |
| Metric | Baseline Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Baseline Accuracy](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa.md?metric=Baseline%20Accuracy>): Higher is better; unit: PERCENT.

- [Best Accuracy](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa.md?metric=Best%20Accuracy>): Higher is better; unit: PERCENT.

- [Final Accuracy](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa.md?metric=Final%20Accuracy>): Higher is better; unit: PERCENT.

- [Net Gain](<https://www.sota2.com/research/sota/biomedical-question-answering-on-pubmedqa.md?metric=Net%20Gain>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Baseline Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ThinkSwitch | 0.6 | Not recorded | 6a1e63ffdbd7150506f85583 |
| ThinkSwitch | 0.43333333333333335 | Not recorded | 6a1e63ffdbd7150506f85583 |

### ThinkSwitch

Baseline Accuracy: 0.6. Result ID: 6a1e76dcfbc373592c17dcbb.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63ffdbd7150506f85583.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e63ffdbd7150506f85583.md>)

Recorded evaluation configuration: {"Model Variant":"thinking"}. This record does not assert independent reproduction.

### ThinkSwitch

Baseline Accuracy: 0.43333333333333335. Result ID: 6a1e76dcfbc373592c17dcba.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63ffdbd7150506f85583.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e63ffdbd7150506f85583.md>)

Recorded evaluation configuration: {"Model Variant":"instruct"}. This record does not assert independent reproduction.

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