Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Judge Accuracy on RMB-SafeRLHF (Target)
Loading...
69
Accuracy
Seed Rubric
63.904
65.227
66.55
67.873
Feb 14, 2026
Accuracy
Delta (Bench - Target)
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Delta (Bench - Target)
Seed Rubric
Judge Model=Qwen3-14B
2026.02
69
0.127
Biased Rubric Search
Judge Model=Qwen3-14B
2026.02
67.4
0.182
Seed Rubric
Judge Model=Qwen3-14B
2026.02
67.3
0.022
Biased Rubric Search
Judge Model=Qwen3-14B
2026.02
64.1
0.062
Feedback
Search any
task
Search any
task