Diagnostic Accuracy on ReMeDi
3.9Accuracy (Neurology)APP-DeepSeek-v3
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| APP-DeepSeek-v3Interaction Setting=Multiple-Turn2025.02 | 3.9 | 3 | 2.86 | 3.59 | |
| APP-QWen-72BInteraction Setting=Multiple-Turn2025.02 | 3.43 | 2.83 | 2.53 | 3.14 | |
| APP-DeepSeek-v3Interaction Setting=One-Shot2025.02 | 3.33 | 2.61 | 2.2 | 3.35 | |
| DeepSeek-v3Interaction Setting=Multiple-Turn2025.02 | 3.28 | 2.83 | 2.13 | 3.17 | |
| Claude-3Interaction Setting=Multiple-Turn2025.02 | 3.23 | 2.44 | 2.2 | 2.98 | |
| LLaMA-70BInteraction Setting=Multiple-Turn2025.02 | 3.19 | 2.11 | 1.66 | 2.93 | |
| GPT-4oInteraction Setting=Multiple-Turn2025.02 | 3.1 | 2.72 | 2.06 | 2.96 | |
| APP-QWen-72BInteraction Setting=One-Shot2025.02 | 3.09 | 2.61 | 2.13 | 3.06 | |
| LLaMA-70BInteraction Setting=One-Shot2025.02 | 3.04 | 1.72 | 1.13 | 2.77 | |
| DeepSeek-v3Interaction Setting=One-Shot2025.02 | 3 | 2.61 | 1.93 | 3.08 | |
| Claude-3Interaction Setting=One-Shot2025.02 | 2.9 | 1.94 | 1.73 | 2.94 | |
| QWen-72BInteraction Setting=Multiple-Turn2025.02 | 2.86 | 2.66 | 1.93 | 3.07 | |
| GPT-4oInteraction Setting=One-Shot2025.02 | 2.81 | 2.27 | 1.93 | 2.9 | |
| QWen-72BInteraction Setting=One-Shot2025.02 | 2.47 | 2.27 | 1.53 | 2.89 |