Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Robustness on JB-R1
Loading...
98.1
Evaluation Score (avg@4)
Self-ReSET
42.668
57.059
71.45
85.841
May 9, 2026
Evaluation Score (avg@4)
Updated 22d ago
Evaluation Results
Method
Method
Links
Evaluation Score (avg@4)
Self-ReSET
Base Model=DeepSeek-R1...
2026.05
98.1
Self-ReSET
Base Model=Qwen3-8B
2026.05
97.4
RECAP
Base Model=DeepSeek-R1...
2026.05
96.3
DAPO
Base Model=DeepSeek-R1...
2026.05
94.9
Self-ReSET
Base Model=DeepSeek-R1...
2026.05
93.2
STAR-1
Base Model=DeepSeek-R1...
2026.05
92
STAR-1
Base Model=Qwen3-8B
2026.05
91.9
DAPO
Base Model=Qwen3-8B
2026.05
91.1
RECAP
Base Model=Qwen3-8B
2026.05
90.3
STAR-1
Base Model=DeepSeek-R1...
2026.05
85.8
RECAP
Base Model=DeepSeek-R1...
2026.05
83.7
DAPO
Base Model=DeepSeek-R1...
2026.05
81.4
Safechain
Base Model=Qwen3-8B
2026.05
73.3
Base
Base Model=Qwen3-8B
2026.05
64.9
Safechain
Base Model=DeepSeek-R1...
2026.05
63.7
Safechain
Base Model=DeepSeek-R1...
2026.05
58
Base
Base Model=DeepSeek-R1...
2026.05
50.6
Base
Base Model=DeepSeek-R1...
2026.05
44.8
Feedback
Search any
task
Search any
task