Safety Research
Can your AI be broken?
63 models tested across 9 escalating jailbreak levels, from basic prompt injection to advanced multi-step attacks.
Tested63
Resisted4
Avg BreakL4.3
Levels
SafeDanger
Curious how these models compare beyond safety?
Sponsored
It gets worse from here
53+ models cracked. Free. No card. No tricks.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy Policy
Same 9 tests. 57 models. Wildly different results.
The full safety benchmark behind this leaderboard. Every prompt, every response, every score.
rival-jailbreak-benchmark.jsonl67 models × 9 levels
L1
L2
L3
L4
L5
L6
L7
L8
L9
claude-opus-..
claude-haiku..
o1
glm-5
claude-sonne..
claude-4.5-s..
codex-mini
claude-3.5-s..
o3
minimax-m2.5
gemini-3.1-p..
qwen3.5-35b-..
qwen3.5-27b
qwen3.5-122b..
qwen3.5-flas..
o4-mini
+51 more models
