Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Judge Accuracy on RMB-SafeRLHF (Bench)
Loading...
85.6
Accuracy
Biased Rubric Search
68.856
73.203
77.55
81.897
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Biased Rubric Search
Judge Model=Qwen3-14B
2026.02
85.6
Seed Rubric
Judge Model=Qwen3-14B
2026.02
81.7
Biased Rubric Search
Judge Model=Qwen3-14B
2026.02
70.3
Seed Rubric
Judge Model=Qwen3-14B
2026.02
69.5
Feedback
Search any
task
Search any
task