Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Feature Engineering on Dia held-out (test)
Loading...
81.3
AUC
Claude Code Raw w/ FELA Skill
79.74
80.145
80.55
80.955
Apr 2, 2026
AUC
Max Score
Updated 16d ago
Evaluation Results
Method
Method
Links
AUC
Max Score
Claude Code Raw w/ FELA Skill
#F=33, Cost ($)=7.44±1.52
2026.04
81.3
82
FELA (MAS)
Time (s)=43200, Cost (...
2026.04
81.2
81.2
Adaptive Skill
#F=55, Time (s)=2301,...
2026.04
81.2
81.3
Claude Code Raw
#F=76, Time (s)=3042,...
2026.04
80.4
81.1
Claude Code Raw w/ MAS Compiler
#F=18, Time (s)=2466,...
2026.04
79.8
80
Feedback
Search any
task
Search any
task