safety benchmark
WMDP
Weapons of Mass Destruction (WMDP) is a multiple-choice benchmark on dual-use biology, chemistry, and cyber knowledge. It measures a model's capacity to enable malicious actors to design, synthesize, acquire, or use chemical, biological, radiological, or nuclear (CBRN) weapons.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
WMDP Ranking
Higher score ranks better on this benchmark.
| 1 | XA | 84.0% | 100.0% | 1 | C |
WMDP Highlights
The leading models and scores on this benchmark.
What is WMDP?
What WMDP measures and how its scores work.
Weapons of Mass Destruction (WMDP) is a multiple-choice benchmark on dual-use biology, chemistry, and cyber knowledge. It measures a model's capacity to enable malicious actors to design, synthesize, acquire, or use chemical, biological, radiological, or nuclear (CBRN) weapons.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- WMDP
- Modality
- text
- Primary category
- safety
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- wmdp|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about WMDP.
Which model scores highest on WMDP?
Grok-4.1 Thinking is currently ranked first with 84.0%.
What does WMDP measure?
Weapons of Mass Destruction (WMDP) is a multiple-choice benchmark on dual-use biology, chemistry, and cyber knowledge. It measures a model's capacity to enable malicious actors to design, synthesize, acquire, or use chemical, biological, radiological, or nuclear (CBRN) weapons.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.