Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Model Evaluation on Text-Coding (test fraction 0.2)
Loading...
80.9
Pair Accuracy
Arena BT
58.228
64.114
70
75.886
Jun 24, 2026
Pair Accuracy
Static ρ
Arena ρ
Public ρ
Updated 29d ago
Evaluation Results
Method
Method
Links
Pair Accuracy
Static ρ
Arena ρ
Public ρ
Arena BT
Reward Model=proprieta...
2026.06
80.9
0.773
1
0.851
Arena Avg Reward
Reward Model=proprieta...
2026.06
80.5
0.779
0.994
0.851
DUALEVAL
Reward Model=proprieta...
2026.06
77.8
0.959
0.878
0.845
Static 2PL
2026.06
73.1
1
0.773
0.763
Arena BT
Reward Model=Skywork-R...
2026.06
68
0.255
0.416
0.511
Arena Avg Reward
Reward Model=Skywork-R...
2026.06
67.3
0.197
0.311
0.432
DUALEVAL
Reward Model=Skywork-R...
2026.06
59.1
0.976
0.805
0.789
Feedback
Search any
task
Search any
task