Medical Reasoning Evaluation on Expert Clinical Annotation Dataset
98.99RelevanceQwen2.5-VL-7B (think)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen2.5-VL-7B (think)Annotator Group=Group 22025.09 | 98.99 | 74.41 | 92.38 | 26.79 | 25.48 | |
| DeepMedix-R1Annotator Group=Group 22025.09 | 98.86 | 79.93 | 95.36 | 73.21 | 74.52 | |
| Qwen2.5-VL-7B (think)Annotator Group=Average2025.09 | 96.03 | 75.31 | 77.29 | 22.92 | 25.84 | |
| DeepMedix-R1Annotator Group=Average2025.09 | 96.01 | 75.03 | 85.92 | 77.08 | 74.16 | |
| DeepMedix-R1Annotator Group=Group 12025.09 | 93.17 | 70.14 | 76.47 | 80.95 | 73.81 | |
| Qwen2.5-VL-7B (think)Annotator Group=Group 12025.09 | 93.08 | 76.22 | 62.2 | 19.05 | 26.19 |