Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Avoid on Avoid 30% corruption (test)
Loading...
84
Success Rate
RoDif
24.72
40.11
55.5
70.89
Jan 31, 2026
Success Rate
Mode Alignment
Updated 3mo ago
Evaluation Results
Method
Method
Links
Success Rate
Mode Alignment
RoDif
2026.01
84
84
CPO
2026.01
78
71
IPO
2026.01
69
58
SimPO
2026.01
27
21
Feedback
Search any
task
Search any
task
