# Clinical Medical Reasoning Evaluation on MMLU ProX Health (random sample)

Source: [Clinical Medical Reasoning Evaluation on MMLU ProX Health (random sample)](<https://www.sota2.com/research/sota/clinical-medical-reasoning-evaluation-on-mmlu-prox-health-random-sample>)

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

Data updated: 2026-02-26T05:39:09.649Z

Evaluation of model performance on the MMLU ProX Health dataset (random sample), specifically assessing clinical medical reasoning capabilities across dimensions like clarity, soundness, safety, and localization.

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 | Clinical Medical Reasoning Evaluation |
| Dataset (including any stated split) | MMLU ProX Health (random sample) |
| Metric | Clarity Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Clarity Score](<https://www.sota2.com/research/sota/clinical-medical-reasoning-evaluation-on-mmlu-prox-health-random-sample.md?metric=Clarity%20Score>): Higher is better; unit: PERCENT.

- [Soundness Score](<https://www.sota2.com/research/sota/clinical-medical-reasoning-evaluation-on-mmlu-prox-health-random-sample.md?metric=Soundness%20Score>): Higher is better; unit: PERCENT.

- [Safety Score](<https://www.sota2.com/research/sota/clinical-medical-reasoning-evaluation-on-mmlu-prox-health-random-sample.md?metric=Safety%20Score>): Higher is better; unit: PERCENT.

- [Localization Score](<https://www.sota2.com/research/sota/clinical-medical-reasoning-evaluation-on-mmlu-prox-health-random-sample.md?metric=Localization%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clarity Score | Result date | Report paper |
| --- | --- | --- | --- |
| MED-COREASONER | 50 | Not recorded | 696722f3e25ad2fa9d1ec009 |
| MED-COREASONER | 26.7 | Not recorded | 696722f3e25ad2fa9d1ec009 |

### MED-COREASONER

Clarity Score: 50. Result ID: 69968a205698665ec4d2aea3.

[Reporting paper](<https://www.sota2.com/research/paper/696722f3e25ad2fa9d1ec009.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696722f3e25ad2fa9d1ec009.md>)

Recorded evaluation configuration: {"Comparison Baseline":"GPT-5.1","Measurement":"Win Rate (%)"}. This record does not assert independent reproduction.

### MED-COREASONER

Clarity Score: 26.7. Result ID: 69968a205698665ec4d2aea4.

[Reporting paper](<https://www.sota2.com/research/paper/696722f3e25ad2fa9d1ec009.md>)

[Method origin paper](<https://www.sota2.com/research/paper/696722f3e25ad2fa9d1ec009.md>)

Recorded evaluation configuration: {"Comparison Baseline":"GPT-5.1","Measurement":"Tie Rate (%)"}. This record does not assert independent reproduction.

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