Multiple Choice Question Answering on CareQA-V MCQ
80.61AccuracyGPT-5.2
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-5.2Model Size=Large, Model Domain=General2026.06 | 80.61 | |
| Aloe-Vision-72BModel Size=>10B, Model Domain=Domain-specific2026.06 | 77.58 | |
| Aloe-Vision-72B-ARModel Size=>10B, Model Domain=Domain-specific2026.06 | 75.76 | |
| Qwen2-VL-72B-InstructModel Size=>10B, Model Domain=General2026.06 | 72.73 | |
| GLM-4.5VModel Size=>10B, Model Domain=Domain-specific2026.06 | 72.73 | |
| Qwen3-VL-30B-A3B-InstructModel Size=>10B, Model Domain=General2026.06 | 71.52 | |
| Lingshu-32BModel Size=>10B, Model Domain=Domain-specific2026.06 | 64.85 | |
| Hulu-Med-32BModel Size=>10B, Model Domain=Domain-specific2026.06 | 63.64 | |
| Aloe-Vision-7B-ARModel Size=<10B, Model Domain=Domain-specific2026.06 | 60.61 | |
| MiMo-VL-7B-RLModel Size=<10B, Model Domain=Domain-specific2026.06 | 59.39 | |
| Hulu-Med-7BModel Size=<10B, Model Domain=Domain-specific2026.06 | 59.39 | |
| Qwen3-VL-8B-InstructModel Size=<10B, Model Domain=General2026.06 | 58.79 | |
| Lingshu-7BModel Size=<10B, Model Domain=Domain-specific2026.06 | 56.97 | |
| Aloe-Vision-7BModel Size=<10B, Model Domain=Domain-specific2026.06 | 56.36 | |
| Kimi-VL-A3B-InstructModel Size=>10B, Model Domain=General2026.06 | 55.15 | |
| HuatuoGPT-Vision-34BModel Size=>10B, Model Domain=Domain-specific2026.06 | 54.55 | |
| Qwen2-VL-7B-InstructModel Size=<10B, Model Domain=General2026.06 | 51.52 | |
| HuatuoGPT-Vision-7BModel Size=<10B, Model Domain=Domain-specific2026.06 | 50.3 | |
| Chiron-o1-8BModel Size=<10B, Model Domain=Domain-specific2026.06 | 47.27 |