Video Description on SVU-31K Full Video Description 1.0 (test)
4.76CIMedScope
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MedScopeTool Use=true, Reasoning=true, Zero-shot=true2026.02 | 4.76 | 4.77 | 4.77 | 4.75 | |
| VideoRFT-7BTool Use=true, Reasoning=true, Zero-shot=true2026.02 | 4.45 | 4.52 | 4.44 | 4.43 | |
| VideoR1-7BTool Use=false, Reasoning=true, Zero-shot=true2026.02 | 4.25 | 4.33 | 4.25 | 4.24 | |
| VideoChat-R1-7BTool Use=true, Reasoning=true, Zero-shot=true2026.02 | 4.01 | 4.12 | 3.92 | 4.02 | |
| LongVT-7B-RFTTool Use=true, Reasoning=true, Zero-shot=true2026.02 | 3.96 | 4.1 | 3.9 | 3.87 | |
| SurgVidLMTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 2.4 | 2.11 | 2.69 | 2.22 | |
| VideoLLaMA3-7BTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 1.66 | 1.71 | 2.21 | 1.86 | |
| InternVL3-8BTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 1.34 | 1.11 | 1.52 | 1.63 | |
| Qwen2.5-VL-7BTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 1.22 | 1.09 | 1.64 | 1.53 | |
| GroundingGPT-7BTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 1.05 | 1.06 | 1.15 | 1.08 | |
| Video-LLaVA-7BTool Use=false, Reasoning=false, Zero-shot=true2026.02 | 1.03 | 1.01 | 1.01 | 1.03 |