ASIMOV-Jailbreak
Embodied agents handle adversarial instructions involving physical safety. Tool-call checks and model judges measure harmful compliance, refusals, and physical safety rubric adherence.
The current release contains 845 multi-turn jailbreak episodes and separate harmful and benign tabletop suites. Dataset access requires accepting conditions. Higher safety compliance is better, while attack success is lower-is-better.
- Made by
- Google DeepMind
- Released
- November 2026
- Kind
- Jailbreaks and prompt injection
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Propensity
- Risk
- Violent crimes
- Behavior
- Harmful use
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator, APIs and tools
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Vision, Robotics, Content safety
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for ASIMOV-Jailbreak yet.
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
3 of 4 checks pass, 1 warning. Look first at the Independent runs check. No scores from any source yet. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 4 notes
- Warning Independent runs No scores from any source yet.
- Note Models scored No models scored yet.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 1 note
- Note Importer No public leaderboard to read.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.