Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Architecture Design on Architecture Design (test)
Loading...
1.028
Loss
Arbor
1.0252
1.0441
1.063
1.0819
Jun 10, 2026
Loss
Delta vs. Init (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Loss
Delta vs. Init (%)
Arbor
2026.06
1.028
6.38
Claude Code
2026.06
1.033
5.92
Codex
2026.06
1.083
1.37
Initial
2026.06
1.098
-
Feedback
Search any
task
Search any
task