List your company

Operating Room Violation Scenario Knowledge Classification on 4D-OR Expert-Authored Challenge Subset

95.86Common Classification ScoreOurs (FT, Ensemble)
32.222448.743765.26581.7863Jun 25, 2025

Evaluation results

MethodLinks
Ours (FT, Ensemble)Fine-tuned=true, Variant=Ensemble2025.0695.8695.6110096.8
Ours (FT, Qwen-Screen)Fine-tuned=true, Variant=Qwen-Screen2025.0691.6395.769995.37
GPT-4o-mini2025.0690.6787.7781.5487.03
Gemini-1.5-Flash2025.068280.7973.0879.18
GPT-4o2025.0675.2978.462.373.37
Qwen2.5-VL-7B-Instruct2025.0673.3157.7369.6465.36
Llama-3.2-11B-Vision-Instruct2025.0663.3375.9863.8569.15
BaichuanMed-OCR-7B2025.0658.667.2152.6660.96
Qwen-vl-plus2025.0657.3575.4152.4664.23
GLM-4.6V-Flash2025.0634.6731.4434.6233.2