List your company
ResearchFormerly WizWand

Medical Visual Question Answering on OMVQA

84.92AccuracyHulu-Med-32B
15.635233.622651.6169.5974Apr 1, 2026Apr 15, 2026Apr 29, 2026May 13, 2026May 27, 2026Jun 10, 2026Jun 25, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Hulu-Med-32BModel Size=>10B, Model Domain=Domain-specific2026.0684.92
InternVL3.5Type=Comprehension only, # Params=8B, # Data=16.3M, Evaluation Protocol=Partially trained on evaluation benchmarks2026.0684.5
Aloe-Vision-72B-ARModel Size=>10B, Model Domain=Domain-specific2026.0683.97
Hulu-Med-7BModel Size=<10B, Model Domain=Domain-specific2026.0683.73
Lingshu-32BModel Size=>10B, Model Domain=Domain-specific2026.0683.45
Lingshu-7BModel Size=<10B, Model Domain=Domain-specific2026.0682.05
Aloe-Vision-72BModel Size=>10B, Model Domain=Domain-specific2026.0681.77
Qwen3-VL-30B-A3B-InstructModel Size=>10B, Model Domain=General2026.0678.47
Lingshu-7BType=Comprehension only, # Params=7B, # Data=7.1M, Evaluation Protocol=Partially trained on evaluation benchmarks2026.0678.4
Qwen3-VL-8B-InstructModel Size=<10B, Model Domain=General2026.0677.78
Aloe-Vision-7B-ARModel Size=<10B, Model Domain=Domain-specific2026.0677.1
Qwen2-VL-72B-InstructModel Size=>10B, Model Domain=General2026.0676.09
Aloe-Vision-7BModel Size=<10B, Model Domain=Domain-specific2026.0675.87
Qwen3-VLType=Comprehension only, # Params=8B, # Data=-, Evaluation Protocol=Partially trained on evaluation benchmarks2026.0675.3
HealthGPT-L14Type=Comprehension only, # Params=14B, # Data=1.5M, Evaluation Protocol=Partially trained on evaluation benchmarks2026.0674.4
GLM-4.5VModel Size=>10B, Model Domain=Domain-specific2026.0673.24
Kimi-VL-A3B-InstructModel Size=>10B, Model Domain=General2026.0673.23
Chiron-o1-8BModel Size=<10B, Model Domain=Domain-specific2026.0672.1
HuatuoGPT-Vision-7BModel Size=<10B, Model Domain=Domain-specific2026.0671.91
MedQwen# Params=7B, Medical VLM=true2026.0470.6
Qwen2-VL-7B-InstructModel Size=<10B, Model Domain=General2026.0670.44
MEDSIGHTType=Unified, # Params=8B, # Data=72K, Evaluation Protocol=Zero-shot inference2026.0668.9
HealthGPT-M3Type=Comprehension only, # Params=3.8B, # Data=1.5M, Evaluation Protocol=Partially trained on evaluation benchmarks2026.0668.5
GPT-5.2Model Size=Large, Model Domain=General2026.0667.74
HuatuoGPT-Vision-34BModel Size=>10B, Model Domain=Domain-specific2026.0667.46
HealthGPT-L14# Params=14B, Medical VLM=true2026.0467.2
HuatuoGPT-VisionType=Comprehension only, # Params=7B, # Data=647K, Evaluation Protocol=Zero-shot inference2026.0666.4
Llama-3.2# Params=11B, Medical VLM=false2026.0463.2
Llama-3.2Type=Comprehension only, # Params=11B, # Data=-, Evaluation Protocol=Zero-shot inference2026.0663.2
MiMo-VL-7B-RLModel Size=<10B, Model Domain=Domain-specific2026.0662.22
MedPLIBType=Unified, # Params=14B/7B, # Data=500K, Evaluation Protocol=Zero-shot inference2026.0661.9
Qwen-2.5-VL# Params=7B, Medical VLM=false2026.0460.8
InternVL2# Params=8B, Medical VLM=false2026.0454.5
InternVL2Type=Comprehension only, # Params=8B, # Data=7.3M, Evaluation Protocol=Zero-shot inference2026.0654.5
Yi-VL# Params=6B, Medical VLM=false2026.0450.2
Yi-VLType=Comprehension only, # Params=6B, # Data=10K, Evaluation Protocol=Zero-shot inference2026.0650.2
LLaVA-v1.5# Params=7B, Medical VLM=false2026.0444.7
LLaVA-v1.5Type=Comprehension only, # Params=7B, # Data=158K, Evaluation Protocol=Zero-shot inference2026.0644.7
LLaVA-MedType=Comprehension only, # Params=7B, # Data=60K, Evaluation Protocol=Zero-shot inference2026.0641.3
HuatuoGPT-Vision# Params=7B, Medical VLM=true2026.0439.9
Med-FlamingoType=Comprehension only, # Params=8.3B, # Data=1.3M, Evaluation Protocol=Zero-shot inference2026.0634.9
HealthGPT-M3# Params=3.8B, Medical VLM=true2026.0432.5
LLaVA-Med# Params=7B, Medical VLM=true2026.0431.8
InstructBLIP# Params=7B, Medical VLM=false2026.0429
InstructBLIPType=Comprehension only, # Params=7B, # Data=364K, Evaluation Protocol=Zero-shot inference2026.0629
BLIP-2# Params=6.7B, Medical VLM=false2026.0426.9
BLIP-2Type=Comprehension only, # Params=6.7B, # Data=-, Evaluation Protocol=Zero-shot inference2026.0626.9
Med-Flamingo# Params=8.3B, Medical VLM=true2026.0424.6
OMG-LLaVAType=Unified, # Params=7B, # Data=1.2M, Evaluation Protocol=Zero-shot inference2026.0618.3