Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on MedQA (AR%, Risk%)
Loading...
100
AR (%)
Always-Act
17.112
38.631
60.15
81.669
May 18, 2026
AR (%)
Risk (%)
Updated 13d ago
Evaluation Results
Method
Method
Links
AR (%)
Risk (%)
Always-Act
alpha=0.20
2026.05
100
31.5
Fixed-Threshold
alpha=0.20
2026.05
86.1
26.9
ACI
alpha=0.20
2026.05
75.2
23.2
SAOCP
alpha=0.20
2026.05
74.8
23.2
NEX-Conf
alpha=0.20
2026.05
56.5
17.2
CSA
alpha=0.20
2026.05
39.4
11.4
ConfFact
alpha=0.20
2026.05
28.4
8
LTT
alpha=0.20
2026.05
24.3
6.9
Naive-Tuning
alpha=0.20
2026.05
20.3
22.5
Feedback
Search any
task
Search any
task