Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Reasoning on MedQA-USMLE Medical Non-MCQ
Loading...
22.6
Accuracy
Data Reformulation
16.776
18.288
19.8
21.312
Oct 10, 2025
Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Accuracy
Data Reformulation
2025.10
22.6
CLARITY
Model Size=7B
2025.10
22.6
PRM RL
2025.10
22.2
GPT-4o
2025.10
22.2
Standard RL
2025.10
19.4
CLARITY
Model Size=3B
2025.10
19.1
Refine-then-Monitor
2025.10
18.3
Qwen2.5
Model Size=3B
2025.10
17.4
Qwen2.5
Model Size=7B
2025.10
17
Feedback
Search any
task
Search any
task