List your company
ResearchFormerly WizWand

Medical Visual Question Answering on PMC-VQA (test)

84.6AccuracyMedCausalX
20.84837.39953.9570.501Aug 18, 2025Sep 23, 2025Oct 29, 2025Dec 5, 2025Jan 10, 2026Feb 15, 2026Mar 24, 2026
Updated 7mo ago

Evaluation results

MethodLinks
MedCausalXfine-tuned=true, evaluation=5-fold cross validation2026.0384.680.235.8
MedVLM-R1fine-tuned=true, evaluation=5-fold cross validation2026.0382.475.245.8
Med-R1fine-tuned=true, evaluation=5-fold cross validation2026.0381.974.547.2
MedCoTfine-tuned=true, evaluation=5-fold cross validation2026.0380.371.850.5
MedRegAfine-tuned=false, evaluation=5-fold cross validation2026.0379.572.849.8
MedDrfine-tuned=false, evaluation=5-fold cross validation2026.0366.266.554.5
LLaVA-Medfine-tuned=false, evaluation=5-fold cross validation2026.0363.855.565.2
InternVLfine-tuned=false, evaluation=5-fold cross validation2026.0361.559.260.8
Qwen2.5-VLfine-tuned=false, evaluation=5-fold cross validation2026.0358.256.763.5
MedEyesBackbone=Qwen2.5-VL-3B, Visual Expert=MedPLIB, Resolution=336x336, Patch size=142025.1155.3——
GMAI-VLCategory=Medical-Specific Models2025.1152.3——
HuatuoGPT-V-7BModel Category=Medical VLM2025.0850——
InternVL3-14BModel Category=General VLM2025.0848.75——
ARMed-RModel Category=Fine-tuned VLM2025.0848.75——
InternVL3-8BModel Category=General VLM2025.0848.55——
Qwen2.5-VL-3BModel Category=Fine-tuned VLM, Fine-tuning protocol=GRPO2025.0848.1——
Qwen2.5-VL-7BModel Category=General VLM2025.0847.8——
Qwen2.5-VL-3BModel Category=Fine-tuned VLM, Fine-tuning protocol=SFT2025.0846.8——
Med-R1Category=Reinforcement Learning Methods2025.1145.8——
RadFMfine-tuned=false, evaluation=5-fold cross validation2026.0345.856.262.8
Qwen2.5-VL-3BModel Category=Fine-tuned VLM, Fine-tuning protocol=Base2025.0845.7——
DeepEyes†Category=Reinforcement Learning Methods, Adaptation=Using the same dataset adapted to medical domains2025.1145.2——
MedVLM-R1Category=Reinforcement Learning Methods2025.1144.8——
GRIT†Category=Reinforcement Learning Methods, Adaptation=Using the same dataset adapted to medical domains2025.1142.3——
GPT-4oCategory=General Vision-Language Models2025.1140.8——
InternVL3-2BModel Category=General VLM2025.0840.69——
InternVL-2Category=General Vision-Language Models2025.1138.4——
Qwen2.5-VL-3BCategory=General Vision-Language Models2025.1137.5——
Med-Flamingofine-tuned=false, evaluation=5-fold cross validation2026.0335.940.573.8
Med-FlamingoCategory=Medical-Specific Models2025.1134.7——
LLaVA-v1.6-13BModel Category=General VLM2025.0834.3——
LLaVA-v1.6-7BModel Category=General VLM2025.0833.05——
RadFMCategory=Medical-Specific Models2025.1125.9——
LLaVA-MedCategory=Medical-Specific Models2025.1124.7——
LLaVA-Med-7BModel Category=Medical VLM2025.0823.8——
MedVInTCategory=Medical-Specific Models2025.1123.3——