Jailbreak Augmented Examples
Models face publicly known jailbreaks applied to prompts from the standard disallowed content set. Scored as not_unsafe rate.
In-house OpenAI evaluation built from public jailbreak techniques.
- Made by
- OpenAI
- Released
- September 2024
- Kind
- Jailbreaks and prompt injection
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- o1 #117 on the capability index
- Last in a system card
- January 2025
- Last model added
- January 2025
5 models share the top score of 100% among models released by January 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in January 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 o1-mini 100%
- 2 o1-preview 100%
- 3 o1 100%
- 4 OpenAI Computer-Using Agent (CUA) 100%
- 5 o3-mini 100%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-mini | 100% | Sep 2024 | Lab model card | |
| 2 | o1-preview | 100% | Sep 2024 | Lab model card | |
| 3 | o1 | 100% | Dec 2024 | Lab model card | |
| 4 | OpenAI Computer-Using Agent (CUA) | 100% | Jan 2025 | Lab model card | |
| 5 | o3-mini | 100% | Jan 2025 | Lab model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
OpenAI’s own number for o1-mini passed 85% in September 2024
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
5 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jan 31, 2025 | o3-mini system card | 100 | Jailbreak Augmented Examples (Table 2) | Robustness |
| Jan 23, 2025 | OpenAI Computer-Using Agent (CUA) system card | 100 | Jailbreak augmented examples, not_unsafe (Table 3) | Robustness |
| Dec 5, 2024 | o1 system card | 100 | Jailbreak augmented examples, not_unsafe (Table 23) | Robustness |
| Sep 12, 2024 | o1-preview system card | 100 | Jailbreak augmented examples, not_unsafe (Table 17) | Robustness |
| Sep 12, 2024 | o1-mini system card | 100 | Jailbreak augmented examples, not_unsafe (Table 17) | Robustness |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
- DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%