# Medical Reasoning on DDXPlus

Source: [Medical Reasoning on DDXPlus](<https://www.sota2.com/research/sota/medical-reasoning-on-ddxplus>)

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

Data updated: 2026-03-31T09:22:08.269Z

Evaluation of model performance on Medical Reasoning using the DDXPlus dataset, reporting key operational metrics including performance score, cost, and inference delay.

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 Reasoning |
| Dataset (including any stated split) | DDXPlus |
| Metric | Performance Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Performance Score](<https://www.sota2.com/research/sota/medical-reasoning-on-ddxplus.md?metric=Performance%20Score>): Higher is better; unit: PERCENT.

- [Cost ($)](<https://www.sota2.com/research/sota/medical-reasoning-on-ddxplus.md?metric=Cost%20(%24)>): Lower is better; unit: OTHER.

- [Inference Delay (h)](<https://www.sota2.com/research/sota/medical-reasoning-on-ddxplus.md?metric=Inference%20Delay%20(h)>): Lower is better; unit: TIME.

## Recorded results

| Method | Performance Score | Result date | Report paper |
| --- | --- | --- | --- |
| ACE | 90.2 | Not recorded | 68fa7be01e209131cea8afd2 |
| Gemini-2.5-pro | 81.1 | Not recorded | 695de87753fdd5c361743c7c |
| EvoRoute | 79.5 | Not recorded | 695de87753fdd5c361743c7c |
| GEPA | 76.4 | Not recorded | 68fa7be01e209131cea8afd2 |
| Base LLM | 75.2 | Not recorded | 68fa7be01e209131cea8afd2 |
| MasRouter | 73.1 | Not recorded | 695de87753fdd5c361743c7c |
| GraphRouter | 62.5 | Not recorded | 695de87753fdd5c361743c7c |
| PromptLLM | 60.07 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4o | 57.58 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4.1 | 55.3 | Not recorded | 695de87753fdd5c361743c7c |
| Qwen3-14b | 41.26 | Not recorded | 695de87753fdd5c361743c7c |

### ACE

Performance Score: 90.2. Result ID: 69cb923c47f34ce924b428aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8afd2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8afd2.md>)

Recorded evaluation configuration: {"Base LLM":"DeepSeek-V3.1-671B","Adaptation Setting":"Offline Adaptation"}. This record does not assert independent reproduction.

### Gemini-2.5-pro

Performance Score: 81.1. Result ID: 6996a2e35698665ec4ec708e.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Setting":"Manual"}. This record does not assert independent reproduction.

### EvoRoute

Performance Score: 79.5. Result ID: 6996a2e35698665ec4ec7093.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Setting":"Ours"}. This record does not assert independent reproduction.

### GEPA

Performance Score: 76.4. Result ID: 69cb923c47f34ce924b428a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8afd2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: {"Base LLM":"DeepSeek-V3.1-671B","Adaptation Setting":"Offline Adaptation"}. This record does not assert independent reproduction.

### Base LLM

Performance Score: 75.2. Result ID: 69cb923c47f34ce924b428a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8afd2.md>)

Recorded evaluation configuration: {"Base LLM":"DeepSeek-V3.1-671B"}. This record does not assert independent reproduction.

### MasRouter

Performance Score: 73.1. Result ID: 6996a2e35698665ec4ec7092.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea7049b.md>)

Recorded evaluation configuration: {"Setting":"Routing"}. This record does not assert independent reproduction.

### GraphRouter

Performance Score: 62.5. Result ID: 6996a2e35698665ec4ec7091.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Setting":"Routing"}. This record does not assert independent reproduction.

### PromptLLM

Performance Score: 60.07. Result ID: 6996a2e35698665ec4ec7090.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Setting":"Routing"}. This record does not assert independent reproduction.

### GPT-4o

Performance Score: 57.58. Result ID: 6996a2e35698665ec4ec708c.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Setting":"Manual"}. This record does not assert independent reproduction.

### GPT-4.1

Performance Score: 55.3. Result ID: 6996a2e35698665ec4ec708d.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Setting":"Manual"}. This record does not assert independent reproduction.

### Qwen3-14b

Performance Score: 41.26. Result ID: 6996a2e35698665ec4ec708f.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Setting":"Manual"}. This record does not assert independent reproduction.

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