Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Ranking Consistency Analysis on MMLU-Pro health Human aging
Loading...
0.62
Spearman Correlation
MedQA
-0.5448
-0.2424
0.06
0.3624
May 19, 2026
Spearman Correlation
Kendall Correlation
Updated 14d ago
Evaluation Results
Method
Method
Links
Spearman Correlation
Kendall Correlation
MedQA
Construction Method=Do...
2026.05
0.62
0.42
SCICUSTOM
Construction Method=Gr...
2026.05
0.49
0.37
MMLU
Construction Method=Do...
2026.05
0.21
0.14
Embedding
Construction Method=Em...
2026.05
0.21
0.1
GPT-5
Construction Method=Sy...
2026.05
0.2
0.18
GPQA
Construction Method=Ge...
2026.05
-0.1
-0.1
IfBench
Construction Method=Ge...
2026.05
-0.32
-0.14
SimpleQA
Construction Method=Ge...
2026.05
-0.5
-0.33
Feedback
Search any
task
Search any
task
