# Medical Dialogue Human-Centric Evaluation on ReMeDi

Source: [Medical Dialogue Human-Centric Evaluation on ReMeDi](<https://www.sota2.com/research/sota/medical-dialogue-human-centric-evaluation-on-remedi>)

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

Data updated: 2026-05-11T09:19:34.379Z

Human evaluation results for models tested on the ReMeDi dataset, focusing on dialogue quality aspects such as Accessibility, Empathy, Relevant Response, and Foster Relation.

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 Dialogue Human-Centric Evaluation |
| Dataset (including any stated split) | ReMeDi |
| Metric | Accessibility |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Accessibility](<https://www.sota2.com/research/sota/medical-dialogue-human-centric-evaluation-on-remedi.md?metric=Accessibility>): Higher is better; unit: SCALAR.

- [Empathy](<https://www.sota2.com/research/sota/medical-dialogue-human-centric-evaluation-on-remedi.md?metric=Empathy>): Higher is better; unit: SCALAR.

- [Relevant Response](<https://www.sota2.com/research/sota/medical-dialogue-human-centric-evaluation-on-remedi.md?metric=Relevant%20Response>): Higher is better; unit: SCALAR.

- [Foster Relation](<https://www.sota2.com/research/sota/medical-dialogue-human-centric-evaluation-on-remedi.md?metric=Foster%20Relation>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accessibility | Result date | Report paper |
| --- | --- | --- | --- |
| APP-DeepSeek-v3 | 4.54 | Not recorded | 68fa7ad61e209131cea856fd |
| Real-world Dialogue | 3.48 | Not recorded | 68fa7ad61e209131cea856fd |
| Calude-3 | 3.18 | Not recorded | 68fa7ad61e209131cea856fd |
| DeepSeek-v3 | 3.1 | Not recorded | 68fa7ad61e209131cea856fd |
| GPT-4o | 2.86 | Not recorded | 68fa7ad61e209131cea856fd |

### APP-DeepSeek-v3

Accessibility: 4.54. Result ID: 6a019f0c47f34ce924e3c322.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Real-world Dialogue

Accessibility: 3.48. Result ID: 6a019f0c47f34ce924e3c321.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bdf1e209131cea30bda.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Calude-3

Accessibility: 3.18. Result ID: 6a019f0c47f34ce924e3c31e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek-v3

Accessibility: 3.1. Result ID: 6a019f0c47f34ce924e3c320.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o

Accessibility: 2.86. Result ID: 6a019f0c47f34ce924e3c31f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad61e209131cea856fd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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