Structured expert probing campaign: radiological and nuclear
Only in system cards
Radiological and nuclear experts test whether a model helps with weapons development steps. Conversations are rated against Preparedness risk levels.
Results are counts of conversations per risk level, not a score.
Made by OpenAI Released Dec 2024 Dangerous capabilities Tasks kept private Last in a system card Jan 2025
Last model added Jan 2025
- Level
- Research frontier Researchers, on open problems or tasks that take days
- Scored
- Graded by people Human experts grade or compare the outputs.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
2
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Structured expert probing campaign: radiological and nuclear yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
2 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 |
|---|---|---|---|---|
| 31 Jan 2025 | o3-mini system card | Structured expert probing campaign, radiological and nuclear, ratings of 123 conversations with the pre-mitigation model only (5.5.1) | Bio and chem risk | |
| 5 Dec 2024 | o1 system card | Structured expert probing campaign, radiological and nuclear, pre-mitigation: 32 of 42 conversations Low, 10 Medium (5.6.1) | Bio and chem risk |
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% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - 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. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%