Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Causal Estimation on Real
Loading...
100
MSA
Structured Pipeline
46.336
60.268
74.2
88.132
Apr 2, 2026
MSA
MRE
Updated 16d ago
Evaluation Results
Method
Method
Links
MSA
MRE
Structured Pipeline
Time (s)=56, Cost ($)=...
2026.04
100
17.8
Adaptive Skill
Time (s)=43, Cost ($)=...
2026.04
96.8
20.7
Auto Opt.
Time (s)=71, Cost ($)=...
2026.04
96.8
15.9
CAIS Skill (Full)
Time (s)=59, Cost ($)=...
2026.04
90.3
24.9
MAS Compiler
Time (s)=115, Cost ($)...
2026.04
90.3
27.3
Claude Code Raw
Time (s)=34, Cost ($)=...
2026.04
87.1
18.3
Knowledge Only
Time (s)=55, Cost ($)=...
2026.04
83.9
22.3
CAIS (MAS)
Time (s)=123, Cost ($)...
2026.04
78.3
32
Tools Only
Time (s)=43, Cost ($)=...
2026.04
48.4
10.8
Feedback
Search any
task
Search any
task