Medical Visual Question Answering (Multiple-choice) on OMVQA (test)
96.8AccuracyMedVR
Evaluation results
| Method | Links | |
|---|---|---|
| MedVRModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain, Backbone=Qwen2.5-VL-7B2026.04 | 96.8 | |
| Lingshu-7BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 84.2 | |
| InternVL2.5-8BModel Category=General-Purpose VLMs, Evaluation Protocol=In-domain2026.04 | 83.9 | |
| InternVL3-14BModel Category=General-Purpose VLMs, Evaluation Protocol=In-domain2026.04 | 81.9 | |
| InternVL3-8BModel Category=General-Purpose VLMs, Evaluation Protocol=In-domain2026.04 | 81.4 | |
| HuatuoGPT-V-7BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 80.1 | |
| Med-R1-2BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 77.3 | |
| MedGemma-4BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 70.5 | |
| Qwen2.5-VL-32BModel Category=General-Purpose VLMs, Evaluation Protocol=In-domain2026.04 | 69.9 | |
| Qwen2.5-VL-7BModel Category=General-Purpose VLMs, Evaluation Protocol=In-domain2026.04 | 59 | |
| MedVLM-R1-2BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 57.4 | |
| LLaVA-Med-7BModel Category=Medical-Specific VLMs, Evaluation Protocol=In-domain2026.04 | 29.3 |