Dental Visual Question Answering on Intraoral Classification II
72.9AccuracyDentalGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| DentalGPTComplex reasoning mode=true2025.12 | 72.9 | |
| GPT-5Complex reasoning mode=true2025.12 | 71 | |
| GPT-4.1Complex reasoning mode=false2025.12 | 70.5 | |
| LLaMA-4-MaverickComplex reasoning mode=false2025.12 | 67.1 | |
| Claude-Sonnet-4.5-ThinkingComplex reasoning mode=true2025.12 | 66.7 | |
| Qwen3-VL-235B-A22B-ThinkingComplex reasoning mode=true2025.12 | 65.7 | |
| Grok-4.1-FastComplex reasoning mode=false2025.12 | 65.2 | |
| Gemini-2.5-Pro-ThinkingComplex reasoning mode=true2025.12 | 65.2 | |
| Ernie-4.5-VL-424B-A47BComplex reasoning mode=true2025.12 | 65.1 | |
| GLM-4.5vComplex reasoning mode=true2025.12 | 64.7 | |
| Phi-4-Multimodal-InstructComplex reasoning mode=false2025.12 | 63.3 | |
| Qwen2.5-VL-7B-InstructComplex reasoning mode=false2025.12 | 61.8 | |
| Gemma-3-27B-itComplex reasoning mode=false2025.12 | 61.4 | |
| Deepseek-VL2Complex reasoning mode=false2025.12 | 59.4 | |
| Claude-Sonnet-4.5Complex reasoning mode=false2025.12 | 59.4 | |
| Mistral-Large-2512Complex reasoning mode=false2025.12 | 58 | |
| Qwen3-VL-235B-A22B-InstructComplex reasoning mode=false2025.12 | 58 |