# Medical Question Answering on MedMCQA (Tau and Speed)

Source: [Medical Question Answering on MedMCQA (Tau and Speed)](<https://www.sota2.com/research/sota/medical-question-answering-on-medmcqa-tau-and-speed>)

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

Data updated: 2026-04-07T09:31:07.933Z

Evaluation of model performance on the MedMCQA dataset for Medical Question Answering, specifically measuring correlation (tau) and inference speedup.

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) | MedMCQA |
| Metric | Tau Correlation |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Tau Correlation](<https://www.sota2.com/research/sota/medical-question-answering-on-medmcqa-tau-and-speed.md?metric=Tau%20Correlation>): Higher is better; unit: SCALAR.

- [Inference Speedup](<https://www.sota2.com/research/sota/medical-question-answering-on-medmcqa-tau-and-speed.md?metric=Inference%20Speedup>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Tau Correlation | Result date | Report paper |
| --- | --- | --- | --- |
| EDA (Ours) | 4.3 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| Full-FT | 3.97 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| EDA (Base) | 3.95 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| LoRA | 3.85 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| EDA (Ours) | 2.85 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| EDA (Base) | 2.45 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| Full-FT | 2.42 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| LoRA | 2.35 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| Training-Free | 2.2 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| Training-Free | 1.42 | Not recorded | 69b0f72d2d603e6de3e45f9c |
| Accuracy Ranking | 0.944 | Not recorded | 68fa7bb61e209131cea8a13e |
| IRT(All) Ranking | 0.928 | Not recorded | 68fa7bb61e209131cea8a13e |
| IRT (pr.) Ranking | 0.928 | Not recorded | 68fa7bb61e209131cea8a13e |

### EDA (Ours)

Tau Correlation: 4.3. Result ID: 69b12f076dbb7075b95bbbcf.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"0","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### Full-FT

Tau Correlation: 3.97. Result ID: 69b12f076dbb7075b95bbbcc.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"0","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### EDA (Base)

Tau Correlation: 3.95. Result ID: 69b12f076dbb7075b95bbbce.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"0","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### LoRA

Tau Correlation: 3.85. Result ID: 69b12f076dbb7075b95bbbcd.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Temperature":"0","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### EDA (Ours)

Tau Correlation: 2.85. Result ID: 69b12f076dbb7075b95bbbd4.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"1","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### EDA (Base)

Tau Correlation: 2.45. Result ID: 69b12f076dbb7075b95bbbd3.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"1","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### Full-FT

Tau Correlation: 2.42. Result ID: 69b12f076dbb7075b95bbbd1.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"1","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### LoRA

Tau Correlation: 2.35. Result ID: 69b12f076dbb7075b95bbbd2.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Temperature":"1","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### Training-Free

Tau Correlation: 2.2. Result ID: 69b12f076dbb7075b95bbbcb.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"0","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### Training-Free

Tau Correlation: 1.42. Result ID: 69b12f076dbb7075b95bbbd0.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72d2d603e6de3e45f9c.md>)

Recorded evaluation configuration: {"Temperature":"1","Target Model":"Meditron3-Qwen2.5-7B"}. This record does not assert independent reproduction.

### Accuracy Ranking

Tau Correlation: 0.944. Result ID: 69d4ceda47f34ce924bcec4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"71","Domain (Format)":"Med Knowledge (MCQ)"}. This record does not assert independent reproduction.

### IRT(All) Ranking

Tau Correlation: 0.928. Result ID: 69d4ceda47f34ce924bcec50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"71","Domain (Format)":"Med Knowledge (MCQ)"}. This record does not assert independent reproduction.

### IRT (pr.) Ranking

Tau Correlation: 0.928. Result ID: 69d4ceda47f34ce924bcec51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"71","Domain (Format)":"Med Knowledge (MCQ)"}. This record does not assert independent reproduction.

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