Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Multimodal Reasoning on MedX
Loading...
29.8
Accuracy
DS-RL + GTP
22.052
24.0635
26.075
28.0865
Jun 30, 2026
Accuracy
Updated 24d ago
Evaluation Results
Method
Method
Links
Accuracy
DS-RL + GTP
Model=Lingshu, Scale=32B
2026.06
29.8
Instruct Model
Model=Lingshu, Scale=32B
2026.06
28.4
DS-RL
Model=Lingshu, Scale=32B
2026.06
28.1
GTP
Model=Lingshu, Scale=32B
2026.06
28
DS-RL + GTP
Model=Lingshu, Scale=7B
2026.06
25.8
GTP
Model=Lingshu, Scale=7B
2026.06
25.75
DS-RL
Model=Lingshu, Scale=7B
2026.06
25
DS-RL + GTP
Model=HuatuoGPT-Vision...
2026.06
23.9
Instruct Model
Model=Lingshu, Scale=7B
2026.06
23.5
GTP
Model=HuatuoGPT-Vision...
2026.06
22.9
DS-RL
Model=HuatuoGPT-Vision...
2026.06
22.55
Instruct Model
Model=HuatuoGPT-Vision...
2026.06
22.35
Feedback
Search any
task
Search any
task