Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pairwise human preference prediction on Music Arena (Overall)
Loading...
0.642
AUC
SVM
0.51304
0.54652
0.58
0.61348
May 5, 2026
AUC
F1
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUC
F1
SVM
Base Model=Model C, Ae...
2026.05
0.642
59.5
SVM
Base Model=Model C, Ae...
2026.05
0.614
52.4
LR
Base Model=Model C, Ae...
2026.05
0.613
55.5
LR
Base Model=Model C, Ae...
2026.05
0.6
54.4
RF
Base Model=Model C, Ae...
2026.05
0.592
52.1
AdaB
Base Model=Model C, Ae...
2026.05
0.574
40
XGB
Base Model=Model C, Ae...
2026.05
0.563
51.3
XGB
Base Model=Model C, Ae...
2026.05
0.562
51.3
RF
Base Model=Model C, Ae...
2026.05
0.558
54.9
Streams
Type=Naive rules
2026.05
0.557
50.9
AdaB
Base Model=Model C, Ae...
2026.05
0.54
25.5
All
Type=Naive rules
2026.05
0.535
49.9
Aesth.
Type=Naive rules
2026.05
0.527
49.8
Likes
Type=Naive rules
2026.05
0.518
47.6
Feedback
Search any
task
Search any
task