Critical View of Safety (CVS) assessment on Nanfang Hospital (SMU) (external val)
87.36Overall CVS ScoreSurg-R1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Surg-R12026.03 | 87.36 | 87.36 | 89.66 | 96.55 | 75.86 | |
| Llama-4-Scout-17B-16E-Instruct2026.03 | 81.61 | 81.61 | 89.66 | 79.31 | 75.86 | |
| Qwen2.5-VL-7B-Surg-CholecT502026.03 | 80.46 | 80.46 | 89.66 | 62.07 | 89.66 | |
| Mistral-Small-3.1-24B-Instruct-25032026.03 | 64.37 | 64.37 | 72.41 | 62.07 | 58.62 | |
| Gemma3-27B-it2026.03 | 63.22 | 63.22 | 89.66 | 86.21 | 13.79 | |
| InternVL3-8B2026.03 | 52.87 | 52.87 | 82.76 | 24.14 | 51.72 | |
| Qwen2.5-VL-7B-Instruct2026.03 | 48.28 | 48.28 | 89.66 | 13.79 | 41.38 | |
| Phi-4-Multimodal2026.03 | 45.98 | 45.98 | 68.97 | 31.03 | 37.93 | |
| MiniCPM-O-2_62026.03 | 40.23 | 40.23 | 68.97 | 10.34 | 41.38 | |
| MiniCPM-V-2_62026.03 | 36.78 | 36.78 | 37.93 | 17.24 | 55.17 | |
| LLaVA-1.5-7B2026.03 | 33.33 | 33.33 | 34.48 | 37.93 | 27.59 |