Contextual Nuclear Knowledge
Models answer 222 multiple choice questions on nuclear engineering with a nonproliferation focus. Scored as cons@32 accuracy.
Questions written by an MIT nuclear security fellow for OpenAI Preparedness.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
OpenAI deep research leads with 77% among models released by Feb 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 Feb 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 OpenAI deep research 77%
- 2 o1 74%
- 3 o3-mini 73%
- 4 GPT-4.5 71%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI deep research | 77% | Feb 2025 | Model card | |
| 2 | o1 | 74% | Dec 2024 | Model card | |
| 3 | o3-mini | 73% | Jan 2025 | Model card | |
| 4 | GPT-4.5 | 71% | Feb 2025 | Model card |
2 models have held number one since its release in Dec 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
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.
4 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 |
|---|---|---|---|---|
| 27 Feb 2025 | GPT-4.5 system card | 71 | Contextual Nuclear Knowledge, cons@32, GPT-4.5 (Post), printed chart label (4.4.1) | Bio and chem risk |
| 25 Feb 2025 | OpenAI deep research system card | 77 | Contextual Nuclear Knowledge, cons@32, post-mitigation with browsing, printed chart label (without browsing 75%) (3.4.5) | Bio and chem risk |
| 31 Jan 2025 | o3-mini system card | 73 | Contextual Nuclear Knowledge, cons@32, o3-mini (Post), printed chart label (5.5.2) | Bio and chem risk |
| 5 Dec 2024 | o1 system card | 74 | Contextual Nuclear Knowledge, accuracy cons@32, o1 (post-mitigation), printed chart label (5.6.2) | 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%