Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reward Modeling on RewardBench 2 (test)
Loading...
76.3
RWBench2 Score
CE-RM-4B
55.708
61.054
66.4
71.746
Jan 28, 2026
RWBench2 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
RWBench2 Score
CE-RM-4B
RM Type=Pointwise, Tra...
2026.01
76.3
Gemini-2.5-Flash
RM Type=Pointwise, Tra...
2026.01
75.9
CE-RM-4B
RM Type=Pointwise, Tra...
2026.01
75.9
CE-RM-4B
RM Type=Pointwise, Tra...
2026.01
74.6
TIR-Judge-Zero-8B
RM Type=Pointwise, Tra...
2026.01
73.4
TIR-Judge-Distill-8B
RM Type=Pointwise, Tra...
2026.01
71.6
TIR-Judge-Zero-4B
RM Type=Pointwise, Tra...
2026.01
68.3
TIR-Judge-Distill-4B
RM Type=Pointwise, Tra...
2026.01
67.3
CompassJudger1-32B
RM Type=Pointwise, Tra...
2026.01
56.5
Feedback
Search any
task
Search any
task