# Medical Question Answering on MedicalQA

Source: [Medical Question Answering on MedicalQA](<https://www.sota2.com/research/sota/medical-question-answering-on-medicalqa>)

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

Data updated: 2026-02-26T05:32:37.285Z

Evaluation of model performance on the MedicalQA dataset for Medical Question Answering, assessed using standard accuracy metrics (ACC%).

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) | MedicalQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 33 of 33 |
| 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-medicalqa.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Symphony-Coord | 86 | Not recorded | 6981818ba8b01e76cc8e2640 |
| MetaGPT | 84 | Not recorded | 6981818ba8b01e76cc8e2640 |
| GPTSwarm | 83 | Not recorded | 6981818ba8b01e76cc8e2640 |
| MetaGPT | 82 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Symphony-Coord | 82 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Symphony-Coord | 81 | Not recorded | 6981818ba8b01e76cc8e2640 |
| AFLOW | 80 | Not recorded | 6981818ba8b01e76cc8e2640 |
| MetaGPT | 80 | Not recorded | 6981818ba8b01e76cc8e2640 |
| AFLOW | 80 | Not recorded | 6981818ba8b01e76cc8e2640 |
| AFLOW | 77 | Not recorded | 6981818ba8b01e76cc8e2640 |
| GPTSwarm | 76 | Not recorded | 6981818ba8b01e76cc8e2640 |
| GPTSwarm | 73 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Morphagent | 64 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Direct | 54 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Synapse | 53 | Not recorded | 6981818ba8b01e76cc8e2640 |
| React | 53 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Consistency | 53 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Refinement | 53 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Synapse | 51 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Direct | 51 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Refinement | 50 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Cold Start | 50 | Not recorded | 6981818ba8b01e76cc8e2640 |
| React | 49 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Consistency | 48 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Cold Start | 48 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Morphagent | 47 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Synapse | 47 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Refinement | 47 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Direct | 45 | Not recorded | 6981818ba8b01e76cc8e2640 |
| React | 44 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Self-Consistency | 43 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Morphagent | 42 | Not recorded | 6981818ba8b01e76cc8e2640 |
| Cold Start | 17 | Not recorded | 6981818ba8b01e76cc8e2640 |

### Symphony-Coord

Accuracy: 86. Result ID: 6999a6005698665ec41c7999.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### MetaGPT

Accuracy: 84. Result ID: 6999a6005698665ec41c7996.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea68673.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### GPTSwarm

Accuracy: 83. Result ID: 6999a6005698665ec41c7998.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### MetaGPT

Accuracy: 82. Result ID: 6999a6005698665ec41c79ac.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea68673.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Symphony-Coord

Accuracy: 82. Result ID: 6999a6005698665ec41c79af.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Symphony-Coord

Accuracy: 81. Result ID: 6999a6005698665ec41c79a4.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### AFLOW

Accuracy: 80. Result ID: 6999a6005698665ec41c7997.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea769ef.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### MetaGPT

Accuracy: 80. Result ID: 6999a6005698665ec41c79a1.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea68673.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### AFLOW

Accuracy: 80. Result ID: 6999a6005698665ec41c79a2.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea769ef.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### AFLOW

Accuracy: 77. Result ID: 6999a6005698665ec41c79ad.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea769ef.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### GPTSwarm

Accuracy: 76. Result ID: 6999a6005698665ec41c79a3.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### GPTSwarm

Accuracy: 73. Result ID: 6999a6005698665ec41c79ae.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Morphagent

Accuracy: 64. Result ID: 6999a6005698665ec41c799f.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b231e209131cea86c88.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Direct

Accuracy: 54. Result ID: 6999a6005698665ec41c799a.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Single Agent"}. This record does not assert independent reproduction.

### Synapse

Accuracy: 53. Result ID: 6999a6005698665ec41c7991.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Single Agent"}. This record does not assert independent reproduction.

### React

Accuracy: 53. Result ID: 6999a6005698665ec41c799b.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Consistency

Accuracy: 53. Result ID: 6999a6005698665ec41c799d.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Refinement

Accuracy: 53. Result ID: 6999a6005698665ec41c799e.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Single Agent"}. This record does not assert independent reproduction.

### Synapse

Accuracy: 51. Result ID: 6999a6005698665ec41c799c.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Single Agent"}. This record does not assert independent reproduction.

### Direct

Accuracy: 51. Result ID: 6999a6005698665ec41c79a5.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Refinement

Accuracy: 50. Result ID: 6999a6005698665ec41c7993.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Single Agent"}. This record does not assert independent reproduction.

### Cold Start

Accuracy: 50. Result ID: 6999a6005698665ec41c7995.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### React

Accuracy: 49. Result ID: 6999a6005698665ec41c7990.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Consistency

Accuracy: 48. Result ID: 6999a6005698665ec41c7992.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Single Agent"}. This record does not assert independent reproduction.

### Cold Start

Accuracy: 48. Result ID: 6999a6005698665ec41c79a0.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3-0324","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Morphagent

Accuracy: 47. Result ID: 6999a6005698665ec41c7994.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b231e209131cea86c88.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Synapse

Accuracy: 47. Result ID: 6999a6005698665ec41c79a7.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Refinement

Accuracy: 47. Result ID: 6999a6005698665ec41c79a9.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Single Agent"}. This record does not assert independent reproduction.

### Direct

Accuracy: 45. Result ID: 6999a6005698665ec41c798f.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3","Category":"Single Agent"}. This record does not assert independent reproduction.

### React

Accuracy: 44. Result ID: 6999a6005698665ec41c79a6.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Single Agent"}. This record does not assert independent reproduction.

### Self-Consistency

Accuracy: 43. Result ID: 6999a6005698665ec41c79a8.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Single Agent"}. This record does not assert independent reproduction.

### Morphagent

Accuracy: 42. Result ID: 6999a6005698665ec41c79aa.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b231e209131cea86c88.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

### Cold Start

Accuracy: 17. Result ID: 6999a6005698665ec41c79ab.

[Reporting paper](<https://www.sota2.com/research/paper/6981818ba8b01e76cc8e2640.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-nano","Category":"Multi-Agent"}. This record does not assert independent reproduction.

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