Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Modeling on UltraFeedback Top-rank 0.4 noisy (test)
Loading...
0.356
Kendall's Tau
Robust PL
0.12928
0.18814
0.247
0.30586
Jul 2, 2026
Kendall's Tau
Top-1 Accuracy
Exact Match Rate
NDCG
Pairwise Accuracy (K=4)
Pairwise Accuracy (Binary)
Updated 22d ago
Evaluation Results
Method
Method
Links
Kendall's Tau
Top-1 Accuracy
Exact Match Rate
NDCG
Pairwise Accuracy (K=4)
Pairwise Accuracy (Binary)
Robust PL
Backbone=Qwen2.5-7B, r...
2026.07
0.356
43.9
14.8
89.7
67.5
68.9
Nominal PL
Backbone=Qwen2.5-7B
2026.07
0.341
43.8
12.8
89
66.6
67.4
Robust PL
Backbone=Qwen2.5-7B, r...
2026.07
0.338
43.8
13.4
89.4
67.8
68.1
Nominal BT
Backbone=Qwen2.5-7B
2026.07
0.138
31.9
8.3
85
56.6
58.1
Feedback
Search any
task
Search any
task