Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factual Knowledge on KoLA WaterBench (test)
Loading...
37.5
GM
AAR
25.02
28.26
31.5
34.74
Dec 18, 2025
GM
TPR
TNR
Updated 1mo ago
Evaluation Results
Method
Method
Links
GM
TPR
TNR
AAR
Model=OPT-1.3B
2025.12
37.5
1
0.695
DualGuard
Model=OPT-1.3B
2025.12
35.5
0.95
0.65
KGW
Model=OPT-1.3B
2025.12
35
0.945
0.68
SIR
Model=OPT-1.3B
2025.12
35
0.975
0.475
Unbiased
Model=OPT-1.3B
2025.12
34.5
0.78
0.635
Original
Model=OPT-1.3B
2025.12
33
-
-
DIPmark
Model=OPT-1.3B
2025.12
33
0.885
0.675
XSIR
Model=OPT-1.3B
2025.12
31.5
0.775
0.975
EWD
Model=OPT-1.3B
2025.12
29.5
0.96
0.78
SWEET
Model=OPT-1.3B
2025.12
28.5
0.825
0.89
SynthID
Model=OPT-1.3B
2025.12
25.5
0.96
0.86
Feedback
Search any
task
Search any
task