Medical Dialogue Human-Centric Evaluation on ReMeDi
4.54AccessibilityAPP-DeepSeek-v3
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| APP-DeepSeek-v32025.02 | 4.54 | 4.6 | 4.48 | 4.54 | |
| Real-world Dialogue2025.02 | 3.48 | 2.78 | 3.24 | 2.92 | |
| Calude-32025.02 | 3.18 | 2.54 | 3.78 | 2.96 | |
| DeepSeek-v32025.02 | 3.1 | 2.42 | 3.5 | 2.56 | |
| GPT-4o2025.02 | 2.86 | 2.34 | 3.38 | 2.56 |