Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Modeling on UltraFeedback Clean (test)
Loading...
0.39
Kendall's τ
Nominal PL
0.33072
0.34611
0.3615
0.37689
Jul 2, 2026
Kendall's τ
Top-1 Acc
Exact Match Acc
NDCG
Pair Acc (K=4)
Pair Acc (Binary)
Updated 22d ago
Evaluation Results
Method
Method
Links
Kendall's τ
Top-1 Acc
Exact Match Acc
NDCG
Pair Acc (K=4)
Pair Acc (Binary)
Nominal PL
Backbone=Qwen2.5-7B
2026.07
0.39
50.1
17.1
0.904
69.2
73.6
Robust PL
Backbone=Qwen2.5-7B, r...
2026.07
0.38
48.3
16.3
0.901
68.7
72.5
Robust PL
Backbone=Qwen2.5-7B, r...
2026.07
0.376
48
16
0.9
68.5
73.5
Nominal BT
Backbone=Qwen2.5-7B
2026.07
0.333
45.2
14
0.888
66.3
69.6
Feedback
Search any
task
Search any
task