Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Calculation on MedCalc-Bench Original (test)
Loading...
73.95
Accuracy
DeepSeek-R1 (MedCalc-R1)
28.5436
40.3318
52.12
63.9082
Feb 10, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
DeepSeek-R1 (MedCalc-R1)
Approach=RL + verifiab...
2026.02
73.95
Qwen3-8B
Approach=RL on recompu...
2026.02
71.4
o1-mini
Approach=RL + verifiab...
2026.02
67.84
RiskAgent-GPT-4o
Approach=Agentic tool...
2026.02
67.71
MedCalc-R1 (3B)
Approach=RL + verifiab...
2026.02
51.34
GPT-4
Approach=Prompting bas...
2026.02
50.9
GPT-4
Approach=Code-exec pro...
2026.02
48.51
GPT-3.5
Approach=Code-exec pro...
2026.02
30.29
Feedback
Search any
task
Search any
task