Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Model Evaluation on Text-Math fraction 0.2 (test)
Loading...
73
Pair Accuracy
Arena BT
59.48
62.99
66.5
70.01
Jun 24, 2026
Pair Accuracy
Static Rho
Arena Rho
Public Rho
Updated 29d ago
Evaluation Results
Method
Method
Links
Pair Accuracy
Static Rho
Arena Rho
Public Rho
Arena BT
Reward Model=proprieta...
2026.06
73
0.571
1
0.86
Arena Avg Reward
Reward Model=proprieta...
2026.06
73
0.571
1
0.86
DUALEVAL
Reward Model=proprieta...
2026.06
68.2
0.99
0.734
0.703
Arena BT
Reward Model=Skywork-R...
2026.06
66.7
0.457
0.624
0.536
Arena Avg Reward
Reward Model=Skywork-R...
2026.06
66.1
0.445
0.639
0.503
Static 2PL
2026.06
64.1
1
0.571
0.682
DUALEVAL
Reward Model=Skywork-R...
2026.06
60
0.984
0.625
0.692
Feedback
Search any
task
Search any
task