Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on Coding
Loading...
102.1
Normalized Score
DUME
76.932
83.466
90
96.534
Mar 31, 2026
Normalized Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Normalized Score
DUME
2026.03
102.1
DUME OOD
2026.03
100.9
Coding expert
2026.03
100
Model averaging
2026.03
97.6
Oracle
2026.03
94
Random routing
2026.03
87
Math expert
2026.03
86
Instr. following expert
2026.03
79.5
Multilingual expert
2026.03
77.9
Feedback
Search any
task
Search any
task