# Machine Reading Comprehension on BioMRC Lite (test)

Source: [Machine Reading Comprehension on BioMRC Lite (test)](<https://www.sota2.com/research/sota/machine-reading-comprehension-on-biomrc-lite-test>)

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

Data updated: 2026-02-26T05:28:22.210Z

Evaluation of Machine Reading Comprehension performance on the test split of the BioMRC Lite dataset, typically measured using 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 | Machine Reading Comprehension |
| Dataset (including any stated split) | BioMRC Lite (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/machine-reading-comprehension-on-biomrc-lite-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| THE UNION OF TWO SINGLE MODELS (IDEAL RESULT) | 92.26 | Not recorded | 68fa6ce41e209131cea368f6 |
| MLP-BASED WEIGHTING MODEL (OURS) | 88 | Not recorded | 68fa6ce41e209131cea368f6 |
| AoA-READER WITH BIOBERT EMBEDDING | 86.74 | Not recorded | 68fa6ce41e209131cea368f6 |
| SCIBERT-MAX-READER | 80.21 | Not recorded | 68fa6ce41e209131cea368f6 |

### THE UNION OF TWO SINGLE MODELS (IDEAL RESULT)

Accuracy: 92.26. Result ID: 698f4a8f3a6c314849f7b76c.

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

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

### MLP-BASED WEIGHTING MODEL (OURS)

Accuracy: 88. Result ID: 698f4a8f3a6c314849f7b76b.

[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: Not recorded. This record does not assert independent reproduction.

### AoA-READER WITH BIOBERT EMBEDDING

Accuracy: 86.74. Result ID: 698f4a8f3a6c314849f7b769.

[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: {"Embedding":"BioBERT"}. This record does not assert independent reproduction.

### SCIBERT-MAX-READER

Accuracy: 80.21. Result ID: 698f4a8f3a6c314849f7b76a.

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

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

Recorded evaluation configuration: {"Backbone":"SciBERT"}. This record does not assert independent reproduction.

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