Surgical Phase Recognition on Renji Hospital (external val)
57.66AccuracySurg-R1
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Surg-R12026.03 | 57.66 | 65.36 | 62.5 | 41.15 | |
| Llama-4-Scout-17B-16E-Instruct2026.03 | 31.38 | 25.64 | 23.46 | 13.41 | |
| Gemma3-27B-it2026.03 | 23.83 | 12.64 | 17.41 | 5.75 | |
| Mistral-Small-3.1-24B-Instruct-25032026.03 | 20.96 | 20.72 | 16.35 | 6.89 | |
| Qwen2.5-VL-7B-Surg-CholecT502026.03 | 20.74 | 36.31 | 27.02 | 10.42 | |
| LLaVA-1.5-7B2026.03 | 20.21 | 11.9 | 8.38 | 3.58 | |
| InternVL3-8B2026.03 | 17.87 | 19.92 | 18.77 | 8.27 | |
| MiniCPM-V-2_62026.03 | 14.68 | 24.54 | 16.01 | 4.85 | |
| Phi-4-Multimodal2026.03 | 10.85 | 13.04 | 13.73 | 2.94 | |
| Qwen2.5-VL-7B-Instruct2026.03 | 10.74 | 1.54 | 14.29 | 1.54 | |
| MiniCPM-O-2_62026.03 | 10.64 | 18.68 | 17.11 | 5.29 |