# Biomedical Question Answering on BioMRC TINY Setting A (test)

Source: [Biomedical Question Answering on BioMRC TINY Setting A (test)](<https://www.sota2.com/research/sota/biomedical-question-answering-on-biomrc-tiny-setting-a-test>)

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

Data updated: 2026-02-26T05:28:22.292Z

Evaluation of Biomedical Question Answering performance on the test split of the BioMRC TINY dataset under Setting A configuration.

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) | BioMRC TINY Setting A (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/biomedical-question-answering-on-biomrc-tiny-setting-a-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AOA-READER WITH BIOBERT EMBEDDING | 93.33 | Not recorded | 68fa6ce41e209131cea368f6 |
| AOA-READER WITH BIOBERT EMBEDDING | 93.33 | Not recorded | 68fa6ce41e209131cea368f6 |
| SCIBERT-MAX-READER | 90 | Not recorded | 68fa6ce41e209131cea368f6 |
| AOA-READER WITH BIOBERT EMBEDDING | 90 | Not recorded | 68fa6ce41e209131cea368f6 |
| AOA-READER WITH BIOBERT EMBEDDING | 90 | Not recorded | 68fa6ce41e209131cea368f6 |
| HUMAN EXPERTS | 85 | Not recorded | 68fa6ce41e209131cea368f6 |
| AOA-READER | 70 | Not recorded | 68fa6ce41e209131cea368f6 |
| AS-READER | 66.67 | Not recorded | 68fa6ce41e209131cea368f6 |

### AOA-READER WITH BIOBERT EMBEDDING

Accuracy: 93.33. Result ID: 698f4a8f3a6c314849f7b784.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Implementation](<https://github.com/leoleoasd/MLP-based-weighting>)

Recorded evaluation configuration: {"Occurrence Aggregation":"max","Token Aggregation":"sum","Train Time":"0.88hr"}. This record does not assert independent reproduction.

### AOA-READER WITH BIOBERT EMBEDDING

Accuracy: 93.33. Result ID: 698f4a8f3a6c314849f7b786.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Implementation](<https://github.com/leoleoasd/MLP-based-weighting>)

Recorded evaluation configuration: {"Occurrence Aggregation":"sum","Token Aggregation":"sum","Train Time":"1.76hr"}. This record does not assert independent reproduction.

### SCIBERT-MAX-READER

Accuracy: 90. Result ID: 698f4a8f3a6c314849f7b781.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c7.md>)

Recorded evaluation configuration: {"Train Time":"83.22hr"}. This record does not assert independent reproduction.

### AOA-READER WITH BIOBERT EMBEDDING

Accuracy: 90. Result ID: 698f4a8f3a6c314849f7b783.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Implementation](<https://github.com/leoleoasd/MLP-based-weighting>)

Recorded evaluation configuration: {"Occurrence Aggregation":"max","Token Aggregation":"max","Train Time":"1.50hr"}. This record does not assert independent reproduction.

### AOA-READER WITH BIOBERT EMBEDDING

Accuracy: 90. Result ID: 698f4a8f3a6c314849f7b785.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Implementation](<https://github.com/leoleoasd/MLP-based-weighting>)

Recorded evaluation configuration: {"Occurrence Aggregation":"sum","Token Aggregation":"max","Train Time":"3.60hr"}. This record does not assert independent reproduction.

### HUMAN EXPERTS

Accuracy: 85. Result ID: 698f4a8f3a6c314849f7b782.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c7.md>)

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

### AOA-READER

Accuracy: 70. Result ID: 698f4a8f3a6c314849f7b780.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa663e1e209131cea0f22c.md>)

Recorded evaluation configuration: {"Train Time":"60.90hr"}. This record does not assert independent reproduction.

### AS-READER

Accuracy: 66.67. Result ID: 698f4a8f3a6c314849f7b77f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce41e209131cea368f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa629e1e209131ce9fa3d7.md>)

[Implementation](<https://github.com/rkadlec/asreader>)

Recorded evaluation configuration: {"Train Time":"16.56hr"}. This record does not assert independent reproduction.

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