# Medical Dialogue Question Answering on CMCQA (test)

Source: [Medical Dialogue Question Answering on CMCQA (test)](<https://www.sota2.com/research/sota/medical-dialogue-question-answering-on-cmcqa-test>)

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

Data updated: 2026-02-26T05:36:43.285Z

Evaluation of model performance on the test split of the CMCQA dataset for Medical Dialogue Question Answering, typically assessed using generation quality metrics like BERTScore and human/LLM preference rankings.

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 Dialogue Question Answering |
| Dataset (including any stated split) | CMCQA (test) |
| Metric | BERTScore Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [BERTScore Precision](<https://www.sota2.com/research/sota/medical-dialogue-question-answering-on-cmcqa-test.md?metric=BERTScore%20Precision>): Higher is better; unit: PERCENT.

- [BERTScore Recall](<https://www.sota2.com/research/sota/medical-dialogue-question-answering-on-cmcqa-test.md?metric=BERTScore%20Recall>): Higher is better; unit: PERCENT.

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

- [GPT-4 Avg Rank](<https://www.sota2.com/research/sota/medical-dialogue-question-answering-on-cmcqa-test.md?metric=GPT-4%20Avg%20Rank>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BERTScore Precision | Result date | Report paper |
| --- | --- | --- | --- |
| MindMap | 94.15 | Not recorded | 68fa72631e209131cea56268 |
| GPT-3.5 | 93.85 | Not recorded | 68fa72631e209131cea56268 |
| BM25 Retriever | 93.65 | Not recorded | 68fa72631e209131cea56268 |
| Embedding Retriever | 93.57 | Not recorded | 68fa72631e209131cea56268 |
| GPT-4 | 93.55 | Not recorded | 68fa72631e209131cea56268 |
| KG Retriever | 93.18 | Not recorded | 68fa72631e209131cea56268 |

### MindMap

BERTScore Precision: 94.15. Result ID: 699236423a6c3148490d57e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

[Implementation](<https://github.com/wyl-willing/MindMap>)

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

### GPT-3.5

BERTScore Precision: 93.85. Result ID: 699236423a6c3148490d57e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

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

### BM25 Retriever

BERTScore Precision: 93.65. Result ID: 699236423a6c3148490d57e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

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

### Embedding Retriever

BERTScore Precision: 93.57. Result ID: 699236423a6c3148490d57ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

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

### GPT-4

BERTScore Precision: 93.55. Result ID: 699236423a6c3148490d57e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

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

### KG Retriever

BERTScore Precision: 93.18. Result ID: 699236423a6c3148490d57eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72631e209131cea56268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6acc1e209131cea2a544.md>)

[Implementation](<https://github.com/zhenjia2017/EXAQT>)

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

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