Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Alignment on Capybara
Loading...
28.34
Win Rate
Clean Data
24.4192
25.4371
26.455
27.4729
Jun 10, 2026
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Clean Data
2026.06
28.34
DeMix-unif
repair=true
2026.06
27.95
DeMix
repair=true
2026.06
27.53
DeMix-unif
repair=false
2026.06
26.82
DeMix
repair=false
2026.06
26.51
DDA-select
2026.06
25.53
Error. Data
2026.06
25.52
DDA-repair
2026.06
24.57
Feedback
Search any
task
Search any
task