Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Success Rate on flames
Loading...
38.6
Success Rate (Raw)
DeepSeek-R1
26.12
29.36
32.6
35.84
Nov 10, 2025
Success Rate (Raw)
Success Rate (Rules)
Success Rate (ML-1)
Success Rate (ML-2)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (Raw)
Success Rate (Rules)
Success Rate (ML-1)
Success Rate (ML-2)
DeepSeek-R1
Model=DeepSeek-R1
2025.11
38.6
20.5
13.4
9.2
GPT-4o
Model=GPT-4o
2025.11
38.5
15
9.8
7
Qwen3-235B
Model=Qwen3-235B
2025.11
26.6
14.6
11.2
8.2
Feedback
Search any
task
Search any
task