Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Robustness on safe-unlearning
Loading...
98
Avg Evaluation Score (k=4)
Self-ReSET
43.816
57.883
71.95
86.017
May 9, 2026
Avg Evaluation Score (k=4)
Updated 22d ago
Evaluation Results
Method
Method
Links
Avg Evaluation Score (k=4)
Self-ReSET
Base Model=Qwen3-8B
2026.05
98
Self-ReSET
Base Model=DeepSeek-R1...
2026.05
97.3
STAR-1
Base Model=Qwen3-8B
2026.05
95.9
Self-ReSET
Base Model=DeepSeek-R1...
2026.05
95.6
RECAP
Base Model=DeepSeek-R1...
2026.05
93.7
DAPO
Base Model=Qwen3-8B
2026.05
89.8
DAPO
Base Model=DeepSeek-R1...
2026.05
88.2
RECAP
Base Model=Qwen3-8B
2026.05
87.9
RECAP
Base Model=DeepSeek-R1...
2026.05
84.9
STAR-1
Base Model=DeepSeek-R1...
2026.05
81.8
DAPO
Base Model=DeepSeek-R1...
2026.05
81.3
STAR-1
Base Model=DeepSeek-R1...
2026.05
79.9
Safechain
Base Model=Qwen3-8B
2026.05
71.7
Safechain
Base Model=DeepSeek-R1...
2026.05
68.6
Safechain
Base Model=DeepSeek-R1...
2026.05
61.8
Base
Base Model=Qwen3-8B
2026.05
49.7
Base
Base Model=DeepSeek-R1...
2026.05
48.4
Base
Base Model=DeepSeek-R1...
2026.05
45.9
Feedback
Search any
task
Search any
task