Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Modeling on LLMBar (test)
Loading...
0.2039
Test MSE (Table)
FCPS
0.20304
0.208845
0.21465
0.220455
May 31, 2026
Test MSE (Table)
Test MSE (Scalar)
Test Delta (Δ)
Test Paired 95% CI (Lower Bound)
Updated 1d ago
Evaluation Results
Method
Method
Links
Test MSE (Table)
Test MSE (Scalar)
Test Delta (Δ)
Test Paired 95% CI (Lower Bound)
FCPS
nM=300
2026.05
0.2039
0.1826
0.0214
0.0186
FCPS
nM=200
2026.05
0.2104
0.1914
0.0189
0.0123
FCPS
nM=100
2026.05
0.2147
0.1972
0.0176
0.0126
FCPS
nM=50
2026.05
0.2213
0.2111
0.0102
0.0033
FCPS
nM=20
2026.05
0.2254
0.2212
0.0042
-0.0036
Feedback
Search any
task
Search any
task