Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following and Safety Alignment on AlpacaEval Borderline
Loading...
98
WinRate
Best-of-N
95.92
96.46
97
97.54
Oct 10, 2025
WinRate
Llama-Guard P(unsafe)
Updated 1d ago
Evaluation Results
Method
Method
Links
WinRate
Llama-Guard P(unsafe)
Best-of-N
Generator=GPT-OSS-20B
2025.10
98
4
SG
Generator=GPT-OSS-20B
2025.10
97
3.1
Threshold filter
Generator=GPT-OSS-20B
2025.10
96
2.1
Feedback
Search any
task
Search any
task
