Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Jailbreak Success Rate on AdvBench (Raw/Rules/ML Metrics)

3.8Raw Jailbreak Success Rate

GPT-4o

1.8242.3372.853.363Nov 10, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
3.8000
2025.11
2.3000
2025.11
1.9000