# Medical Question Answering on Aggregate MedQA MedMCQA PubMedQA MMLU

Source: [Medical Question Answering on Aggregate MedQA MedMCQA PubMedQA MMLU](<https://www.sota2.com/research/sota/medical-question-answering-on-aggregate-medqa-medmcqa-pubmedqa-mmlu>)

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

Data updated: 2026-02-26T05:29:43.648Z

Evaluation of model performance across an aggregate benchmark combining MedQA, MedMCQA, PubMedQA, and MMLU datasets for Medical Question Answering, typically measured by average 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 | Medical Question Answering |
| Dataset (including any stated split) | Aggregate MedQA MedMCQA PubMedQA MMLU |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/medical-question-answering-on-aggregate-medqa-medmcqa-pubmedqa-mmlu.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MedAgents | 86.7 | Not recorded | 68fa73701e209131cea5c7d9 |
| MedAgents | 72.1 | Not recorded | 68fa73701e209131cea5c7d9 |
| Few-shot CoT | 71.2 | Not recorded | 68fa73701e209131cea5c7d9 |

### MedAgents

Accuracy: 86.7. Result ID: 6992eb3b3a6c314849125b54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7d9.md>)

[Implementation](<https://github.com/gersteinlab/MedAgents>)

Recorded evaluation configuration: {"Backbone":"GPT-4","Evaluation Protocol":"zero-shot setting"}. This record does not assert independent reproduction.

### MedAgents

Accuracy: 72.1. Result ID: 6992eb3b3a6c314849125b53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7d9.md>)

[Implementation](<https://github.com/gersteinlab/MedAgents>)

Recorded evaluation configuration: {"Backbone":"GPT-3.5","Evaluation Protocol":"zero-shot setting"}. This record does not assert independent reproduction.

### Few-shot CoT

Accuracy: 71.2. Result ID: 6992eb3b3a6c314849125b52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73701e209131cea5c7d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"Flan-PaLM","Evaluation Protocol":"few-shot setting"}. This record does not assert independent reproduction.

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