Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
QA on MedCalc
Loading...
0.0157
MAE
GRPO
0.008068
0.059584
0.1111
0.162616
Jun 8, 2026
MAE
Updated 1mo ago
Evaluation Results
Method
Method
Links
MAE
GRPO
Target Ratio (rt)=0.05
2026.06
0.0157
DPO
Target Ratio (rt)=0.05
2026.06
0.0479
Temp Scaling
Target Ratio (rt)=0.05
2026.06
0.0653
No Defense
Target Ratio (rt)=0.05
2026.06
0.2051
Subsampling
Target Ratio (rt)=0.05
2026.06
0.2065
Feedback
Search any
task
Search any
task
