Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Win Rate Evaluation on ANTHROPIC HH (test)
Loading...
88.82
Win Rate
TOSS
38.3072
51.4211
64.535
77.6489
Mar 1, 2026
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
TOSS
Comparison model=Stand...
2026.03
88.82
TOSS
Paradigm=Training-base...
2026.03
88.82
TOSS
Comparison model=SEAL,...
2026.03
84.54
SafetyLock
Paradigm=Training-free...
2026.03
50.25
Standard SFT
Paradigm=/, Base Model...
2026.03
50
Circuit Breakers
Paradigm=Training-base...
2026.03
40.25
Feedback
Search any
task
Search any
task