Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Medical Question Answering on PMC v1.0 (test)
Loading...
0.5855
Accuracy
GPT-4o
0.333092
0.398621
0.46415
0.529679
Aug 4, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-4o
Open Weights=false, Op...
2025.08
0.5855
MedVLThinker-32B RL
Open Weights=true, Ope...
2025.08
0.5437
HuatuoGPT-Vision-7B
Open Weights=true, Ope...
2025.08
0.5339
Qwen2.5-VL-32B-Instruct
Open Weights=true, Ope...
2025.08
0.5328
HuatuoGPT-Vision-34B
Open Weights=true, Ope...
2025.08
0.5254
Gemme 3 27B
Open Weights=true, Ope...
2025.08
0.5205
GPT-4o-mini
Open Weights=false, Op...
2025.08
0.519
MedVLThinker-7B RL
Open Weights=true, Ope...
2025.08
0.5067
Qwen2.5-VL-7B-Instruct
Open Weights=true, Ope...
2025.08
0.493
MedVLThinker-3B RL
Open Weights=true, Ope...
2025.08
0.4732
Qwen2.5-VL-3B-Instruct
Open Weights=true, Ope...
2025.08
0.4477
Gemme 3 4B
Open Weights=true, Ope...
2025.08
0.4442
MedGemma 4B
Open Weights=true, Ope...
2025.08
0.4273
MedGemma 27B
Open Weights=true, Ope...
2025.08
0.3675
Llava Med v1.5 Mistral 7B
Open Weights=true, Ope...
2025.08
0.3428
Feedback
Search any
task
Search any
task