Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (Spearman rho, Resolution Gain)
Loading...
1
Spearman rho Agreement (FullPair)
FullPair
0.064
0.307
0.55
0.793
May 28, 2026
Spearman rho Agreement (FullPair)
Resolution Gain
Updated 1mo ago
Evaluation Results
Method
Method
Links
Spearman rho Agreement (FullPair)
Resolution Gain
FullPair
Protocol=FullPair
2026.05
1
1.88
Pointwise
Protocol=Pointwise
2026.05
0.95
1.18
SEAL
Protocol=SEAL
2026.05
0.95
2.1
FlatBrk
Protocol=FlatBrk
2026.05
0.93
1.77
Listwise
Protocol=Listwise
2026.05
0.69
9.84
Original
Protocol=Original
2026.05
0.43
1
FixedRub
Protocol=FixedRub
2026.05
0.1
0.12
Feedback
Search any
task
Search any
task
