THE JAILBREAK INDEX

Definitive Analysis & Exploits 2024-2025

53 Models Analyzed
67.3% Extremely Vulnerable
Dec 10, 2025 Last Updated

🤖 DeepSeek Models

DeepSeek-R1

Difficulty: 1

Success Rate

100%

Method

Skeleton Key

JAILBREAKER NOTE: One of the easiest reasoning models so far. Simple skeleton key and role play required.

🔓 VIEW EXPLOIT

DeepSeek Chat

Difficulty: 1

Success Rate

100%

Method

DAN / Force

JAILBREAKER NOTE: Very unsafe model, I swear even DAN could work with some effort :p

🔓 VIEW EXPLOIT

🚀 Grok Models (xAI)

Grok 3

Difficulty: 1

Success Rate

100%

Method

Roleplay + Noise

JAILBREAKER NOTE: Old and easy model. Role playing/Personna + noise will work like a charm. And with an actual DAN working!

🔓 VIEW EXPLOIT

Grok 4

Difficulty: 1

Success Rate

99%

Method

Direct Injection

JAILBREAKER NOTE: Very similar to grok 3, Role playing + noise works perfectly. And DAN is still here :p

🔓 VIEW EXPLOIT

🔍 Google Models (Gemini/Gemma)

Gemini 2.5 Flash

Difficulty: 1

Success Rate

100%

Method

Grandma Trick

JAILBREAKER NOTE: One of the easiest models to jailbreak. Still falls for the grandma trick :)

🔓 VIEW EXPLOIT

Gemini 2.5 Pro

Difficulty: 2

Success Rate

90%

Method

Immersive RP

JAILBREAKER NOTE: Safetyless Reasoning model. Goes fully immerssed in role playing.

🔓 VIEW EXPLOIT

Gemini 3 Pro

Difficulty: 3

Success Rate

Medium

Method

System Prompt

JAILBREAKER NOTE: Strong model. Need context overload or Long Multi Shot, try to avoid CBRN.

(put as system prompt)

🔓 VIEW EXPLOIT

Gemma-2-9B

Difficulty: 1

Success Rate

94%

Method

Basic Bypass

JAILBREAKER NOTE: All of Googles open source models are relativily easy to jailbreak. no magic trick needed.

🔓 VIEW EXPLOIT

Gemma-7B

Difficulty: 1

Success Rate

100%

Method

Adaptive

JAILBREAKER NOTE: Just a more capable version of Gemma 2b. no better safety training!

🔓 VIEW EXPLOIT

🌪️ Mistral Models

Mistral Magistral

Difficulty: 1

Success Rate

92%

Method

Cyph3r Attack

JAILBREAKER NOTE: Improved safety training. but remains very doable using noise and role play.

🔓 VIEW EXPLOIT

Mistral-7B

Difficulty: 1

Success Rate

95%

Method

Persona

JAILBREAKER NOTE: Easy model. Using personna is recommanded, everything should work.

🔓 VIEW EXPLOIT

Mistral Large

Difficulty: 2

Success Rate

87%

Method

Roleplay

JAILBREAKER NOTE: Not much safety training. Follows any instructions with personna or role play!

🔓 VIEW EXPLOIT

🤖 OpenAI GPT Models

GPT-3.5 Turbo

Difficulty: 1

Success Rate

100%

Method

Roleplay

JAILBREAKER NOTE: An old model we all loved and liked. Even do the generated content wasn't that good :> Role play will do it all.

🔓 VIEW EXPLOIT

GPT-4

Difficulty: 1

Success Rate

96%

Method

Context Overload

JAILBREAKER NOTE: Effort is required. Need a bit of context overload and consitant personna/role play. Noise to the main request is also required.

🔓 VIEW EXPLOIT

GPT-4 Turbo

Difficulty: 1

Success Rate

96%

Method

Adaptive

JAILBREAKER NOTE: Similar to GPT 4, but with faster generation speed.

🔓 VIEW EXPLOIT

GPT-4o

Difficulty: 3

Success Rate

67%

Method

Strict Persona

JAILBREAKER NOTE: A LOT of noise/context overload is required. And it's a personna strict generation rules may help.

🔓 VIEW EXPLOIT

GPT-5-main

Difficulty: 2

Success Rate

78%

Method

System Message

JAILBREAKER NOTE: Suprisingly easier model? at least in comparaison to GPT-4o, Impressionning system message is very useful.

🔓 VIEW EXPLOIT

GPT-5-thinking 🏆

Difficulty: 5

Success Rate

20%

Method

Zero-Reasoning (API)

JAILBREAKER NOTE: Most secure model out there. Keeps zeroing user request. (Note: Exploit works ONLY in API by injecting no reasoning instructions).

🔓 VIEW EXPLOIT

🧠 Anthropic Claude Models

Legacy Models

Claude 2.0 / 2.1 / 3.0

Difficulty: 1

Success Rate

100%

Method

Game Context

JAILBREAKER NOTE: Old models with poor safety training. Game context and persona will do it.

🔓 VIEW EXPLOIT

Claude 3 Opus

Difficulty: 1

Success Rate

100%

Method

Persona

JAILBREAKER NOTE: Better safety training but dosen't resist much. Personna will do it.

🔓 VIEW EXPLOIT

Modern Claude Series

Claude 3.5 Sonnet

Difficulty: 2

Success Rate

1.3%

Method

Context Overload

JAILBREAKER NOTE: Much secure model. Will require some context overload and effort.

🔓 VIEW EXPLOIT

Claude 3.7 Sonnet

Difficulty: 2

Success Rate

2.5%

Method

Chain of Draft

JAILBREAKER NOTE: Similar to 3.5 but maybe even easier. Role play is fine.

🔓 VIEW EXPLOIT

Claude Sonnet 4 / Opus 4.1 ⚠️

Difficulty: 1

Success Rate

92%

Method

API Attack

JAILBREAKER NOTE: Not that of a secure model. multiple attack possible, Especially on API.

🔓 VIEW EXPLOIT

Claude Haiku 4.5 🥇

Difficulty: 2

Success Rate

0.9%

Method

Multi-shot

JAILBREAKER NOTE: Secure model. Can be jailbroken after multi-shot or very well made instructions.

🔓 VIEW EXPLOIT

Claude Sonnet 4.5

Difficulty: 2

Success Rate

Unknown

Method

Enterprise JB

JAILBREAKER NOTE: Not a very secure model. But the safety filters makes it much harder.

🔓 VIEW EXPLOIT

Claude Opus 4.5 🏆

Difficulty: 4

Success Rate

Unknown

Method

TBD

JAILBREAKER NOTE: Very hard model. Similar to haiku 4.5 but has much better safety on multi-shot.

🦙 Meta Llama Models

Llama 2 Chat

Difficulty: 1

Success Rate

100%

Method

Uncensored

JAILBREAKER NOTE: Not a secure model, very old and has massive amount of vulnerabilitys.

🔓 VIEW EXPLOIT

Llama 3-70B

Difficulty: 1

Success Rate

89%

Method

Programmatic

No specific jailbreaker note provided.

📚 References & Citations

This index compiles data from academic papers, security research, red teaming reports, and official system cards. Key sources include:

⚠️ Disclaimer: This index is for educational and research purposes only. Data is compiled from publicly available sources and may not reflect the most current model versions. Always consult official documentation and conduct your own security assessments before deploying AI models in production environments.

⚡ Jailbreak Legends