# Medical Differential Diagnoses on DDXPlus

Source: [Medical Differential Diagnoses on DDXPlus](<https://www.sota2.com/research/sota/medical-differential-diagnoses-on-ddxplus>)

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

Data updated: 2026-03-27T14:08:50.288Z

Evaluation of model performance on Medical Differential Diagnoses using the DDXPlus dataset, reporting accuracy, diversity, and efficiency metrics.

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 Differential Diagnoses |
| Dataset (including any stated split) | DDXPlus |
| Metric | Avg Correct |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

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

- [Diversity](<https://www.sota2.com/research/sota/medical-differential-diagnoses-on-ddxplus.md?metric=Diversity>): Higher is better; unit: PERCENT.

- [Efficiency](<https://www.sota2.com/research/sota/medical-differential-diagnoses-on-ddxplus.md?metric=Efficiency>): Lower is better; unit: SCALAR.

- [Top-1 Acc.](<https://www.sota2.com/research/sota/medical-differential-diagnoses-on-ddxplus.md?metric=Top-1%20Acc.>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Correct | Result date | Report paper |
| --- | --- | --- | --- |
| Multi-Answer RLVR | 79 | Not recorded | 69c60ee60636e5bf4afc838f |
| Multi-Answer RLCR | 77 | Not recorded | 69c60ee60636e5bf4afc838f |
| RLVR (Single Loss + Multi Prompt) | 67 | Not recorded | 69c60ee60636e5bf4afc838f |
| RLCR (Single Loss + Single Prompt) | 65 | Not recorded | 69c60ee60636e5bf4afc838f |
| RLVR (Single Loss + Single Prompt) | 62 | Not recorded | 69c60ee60636e5bf4afc838f |
| RLCR (Single Loss + Multi Prompt) | 49 | Not recorded | 69c60ee60636e5bf4afc838f |
| Zero-Shot (Multi Prompt) | 41 | Not recorded | 69c60ee60636e5bf4afc838f |
| Zero-Shot (Multi Prompt) | 31 | Not recorded | 69c60ee60636e5bf4afc838f |

### Multi-Answer RLVR

Avg Correct: 79. Result ID: 69c68e9b47f34ce924b0d10f.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Implementation](<https://github.com/ishapuri/multi_answer_rl>)

Recorded evaluation configuration: {"Loss type":"Multi Loss","Prompting strategy":"Multi Prompt","k-value":"3"}. This record does not assert independent reproduction.

### Multi-Answer RLCR

Avg Correct: 77. Result ID: 69c68e9b47f34ce924b0d113.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Implementation](<https://github.com/ishapuri/multi_answer_rl>)

Recorded evaluation configuration: {"Loss type":"Multi Loss","Prompting strategy":"Multi Prompt","k-value":"3"}. This record does not assert independent reproduction.

### RLVR (Single Loss + Multi Prompt)

Avg Correct: 67. Result ID: 69c68e9b47f34ce924b0d10d.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89a85.md>)

Recorded evaluation configuration: {"Loss type":"Single Loss","Prompting strategy":"Multi Prompt","k-value":"3"}. This record does not assert independent reproduction.

### RLCR (Single Loss + Single Prompt)

Avg Correct: 65. Result ID: 69c68e9b47f34ce924b0d110.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a241e209131cea81436.md>)

Recorded evaluation configuration: {"Loss type":"Single Loss","Prompting strategy":"Single Prompt","k-value":"3"}. This record does not assert independent reproduction.

### RLVR (Single Loss + Single Prompt)

Avg Correct: 62. Result ID: 69c68e9b47f34ce924b0d10c.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89a85.md>)

Recorded evaluation configuration: {"Loss type":"Single Loss","Prompting strategy":"Single Prompt","k-value":"3"}. This record does not assert independent reproduction.

### RLCR (Single Loss + Multi Prompt)

Avg Correct: 49. Result ID: 69c68e9b47f34ce924b0d111.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a241e209131cea81436.md>)

Recorded evaluation configuration: {"Loss type":"Single Loss","Prompting strategy":"Multi Prompt","k-value":"3"}. This record does not assert independent reproduction.

### Zero-Shot (Multi Prompt)

Avg Correct: 41. Result ID: 69c68e9b47f34ce924b0d112.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

Recorded evaluation configuration: {"Prompting strategy":"Multi Prompt","k-value":"3","Comparison Baseline":"RLCR group"}. This record does not assert independent reproduction.

### Zero-Shot (Multi Prompt)

Avg Correct: 31. Result ID: 69c68e9b47f34ce924b0d10e.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee60636e5bf4afc838f.md>)

Recorded evaluation configuration: {"Prompting strategy":"Multi Prompt","k-value":"3","Comparison Baseline":"RLVR group"}. This record does not assert independent reproduction.

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