List your company
ResearchFormerly WizWand

Medical Visual Question Answering on MMMU Health & Medicine (test)

74.5AccuracyOpenAI-o3
25.137.92550.7563.575Nov 27, 2025Dec 19, 2025Jan 10, 2026Feb 2, 2026Feb 24, 2026Mar 18, 2026Apr 10, 2026
Updated 7mo ago

Evaluation results

MethodLinks
OpenAI-o3Category=Close-Source SOTA2026.0474.5
GPT-4.1Category=Close-Source SOTA2026.0473.6
Gemini 2.5 ProCategory=Close-Source SOTA2026.0472.8
GPT-5Category=Close-Source SOTA2026.0470.7
InternVL3-8BCategory=Open-Source SOTA2026.0462.3
Qwen2.5-VL-32BCategory=Open-Source SOTA2026.0460.1
HuatuoGPT-Vision-34BCategory=Medical MLLMs2026.0460.1
MedEyesBackbone=Qwen2.5-VL-3B, Visual Expert=MedPLIB, Resolution=336x336, Patch size=142025.1159.7
MMedAgent-RL-7BCategory=Multimodal Medical Agents2026.0458.9
PixelReasoner-RL-v1-7BCategory=MLLMs can Think with Images2026.0458
DeepEyes-7BCategory=MLLMs can Think with Images2026.0457.8
Mini-o3-7B-v1Category=MLLMs can Think with Images2026.0457.4
VILA-M3-40BCategory=Multimodal Medical Agents2026.0456.6
MedLVRCategory=MLLMs can Think with Images2026.0456.6
MedAgent-ProCategory=Multimodal Medical Agents2026.0452.9
InternVL-2Category=General Vision-Language Models2025.1152.7
GMAI-VLCategory=Medical-Specific Models2025.1151.2
GRIT†Category=Reinforcement Learning Methods, Adaptation=Using the same dataset adapted to medical domains2025.1149.5
AURACategory=Multimodal Medical Agents2026.0449.3
DeepEyes†Category=Reinforcement Learning Methods, Adaptation=Using the same dataset adapted to medical domains2025.1149.1
Med-FlamingoCategory=Medical-Specific Models2025.1147.5
Qwen2.5-VL-7BCategory=MLLMs can Think with Images2026.0446.4
MedVLM-R1Category=MLLMs can Think about Images2026.0445.9
Med-R1Category=MLLMs can Think about Images2026.0444.7
MMedAgent-7BCategory=Multimodal Medical Agents2026.0444.1
MEDVISTAGYMBackbone=Qwen3vl-8B, Category=MLLMs can Think with Images2026.0442.9
LLaVA-Next-13BCategory=Open-Source SOTA2026.0440.1
SMR-AgentsCategory=Multimodal Medical Agents2026.0440.1
LLaVA-Med-7BCategory=Medical MLLMs2026.0438.8
LLaVA-v1.5-8BCategory=Open-Source SOTA2026.0438.2
LLaVA-MedCategory=Medical-Specific Models2025.1136.9
MedVLM-R1Category=Reinforcement Learning Methods2025.1135.5
Qwen2.5-VL-3BCategory=General Vision-Language Models2025.1134.3
LLaVA-Next-7BCategory=Open-Source SOTA2026.0433.1
Med-R1Category=Reinforcement Learning Methods2025.1132.7
MedVInTCategory=Medical-Specific Models2025.1128.3
Med-FlamingoCategory=Medical MLLMs2026.0428.3
RadFMCategory=Medical-Specific Models2025.1127
RadFMCategory=Medical MLLMs2026.0427