Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge-intensive Multiple-Choice QA on MMLU
Loading...
1
Spearman Rho
SEAL
0.6984
0.7767
0.855
0.9333
May 28, 2026
Spearman Rho
Resolution Gain
Updated 1mo ago
Evaluation Results
Method
Method
Links
Spearman Rho
Resolution Gain
SEAL
Protocol=SEAL
2026.05
1
1.3
FullPair
Protocol=FullPair
2026.05
1
1.77
FixedRub
Protocol=FixedRub
2026.05
0.95
0.77
FlatBrk
Protocol=FlatBrk
2026.05
0.93
1.3
Pointwise
Protocol=Pointwise
2026.05
0.86
1.13
Original
Protocol=Original
2026.05
0.79
1
Listwise
Protocol=Listwise
2026.05
0.71
3.52
Feedback
Search any
task
Search any
task
