Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reward Modeling on SummEval (test)
Loading...
0.0444
MSE (Table)
FCPS
0.0439
0.047275
0.05065
0.054025
May 31, 2026
MSE (Table)
MSE (Scalar)
Delta MSE
95% CI (Paired)
Updated 1d ago
Evaluation Results
Method
Method
Links
MSE (Table)
MSE (Scalar)
Delta MSE
95% CI (Paired)
FCPS
nM=800
2026.05
0.0444
0.0435
0.0009
-0.0001
FCPS
nM=512
2026.05
0.0448
0.0436
0.0011
0.0002
FCPS
nM=256
2026.05
0.0451
0.046
-0.0009
-0.0022
FCPS
nM=128
2026.05
0.0485
0.0474
0.0011
-0.0006
FCPS
nM=64
2026.05
0.0528
0.0501
0.0026
0.0004
FCPS
nM=32
2026.05
0.0569
0.0511
0.0058
0.0032
Feedback
Search any
task
Search any
task
