CBRN open-ended questions
Experts review model answers to single and multi-turn CBRN threat scenario questions for accuracy, novelty and actionable uplift.
In-house Google DeepMind evaluation. Results are usually qualitative.
- Made by
- Google DeepMind
- Released
- March 2025
- Kind
- Hazardous knowledge
- Level
- Expert
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a system card
- November 2025
- Last model added
- November 2025
3
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for CBRN open-ended questions yet.
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.
3 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 |
|---|---|---|---|---|
| Nov 18, 2025 |  Gemini 3 Pro system card | Open-Ended Questions: high scientific accuracy, low novelty, insufficient detail for low-medium resourced actors, no score (CBRN, p.7) | Bio and chem risk | |
| Jul 7, 2025 | Gemini 2.5 Pro technical report | CBRN open-ended questions (bio, radiological, nuclear), qualitative expert assessment, no score: detailed and accurate but not consistently enabling key bottleneck steps (Section 5.7) | Bio and chem risk | |
| Apr 28, 2025 | Gemini 2.5 Pro model card | CBRN open-ended questions (bio, radiological, nuclear), qualitative expert assessment, no score (CBRN section) | Bio and chem risk |
More in Biology and chemistry
- GeneBench Pro In use Agents analyze messy simulated genomics and biology datasets to estimate a decision-relevant quantity across 129 problems. Scored automatically against known answers. GPT-5.6 Sol 31.5%
- SUPERChem In use Models solve 500 expert-written chemistry reasoning problems, offered in multimodal and text-only forms. Expert solution paths also allow a reasoning path score.
Tencent Hy4 preview 66.4% - LifeSciBench In use Models complete 750 expert-written life science research tasks, often with attached figures, tables, or sequence files. Graded against expert rubrics as score and pass rate. GPT-Rosalind-6 61.3%
- MedChemBench (OpenAI) In use Models answer chemistry questions from an OpenAI internal set, grouped with OpenAI's life science research evaluations. OpenAI has not published the task format. GPT-Rosalind-6 49.6%
- ProtocolQA Open-Ended In use Models correct errors in published lab protocols using open-ended questions adapted from LAB-Bench ProtocolQA. Scored as pass@1. GPT-6 Cyber 47.2%
- MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. gpt-oss-120b 47.5%