Should citizens be required to hold a national digital identity card?
Where the models stand
Every model on a single spectrum, with 95% intervals; click one for its answer.
Whiskers show the 95% interval across reruns. Click a model to read its answer and the markers the classifier pulled.
The short answer
On a national digital ID, Grok strongly opposes (value -0.9), while DeepSeek leans support (0.12). ChatGPT (-0.03), Claude (-0.05), Gemini (0.0), and Llama (0.0) are balanced, with values near zero.
The field is divided with a spread of 0.68. Gemini, Grok, and Llama show perfect stability (100%), Claude is 77% stable, DeepSeek 73%, and ChatGPT 63%. No model refused to answer (0% refusal).
- Grok is the most opposed model at -0.9.
- DeepSeek leans support with a value of 0.12.
- Gemini, Grok, and Llama have 100% stability.
How the field splits
The models clustered by where they landed.
Holds the center
These models are balanced near zero (values from -0.05 to 0.0) and often mention surveillance concerns but do not take a strong side.
Firmly toward oppose
Grok strongly opposes with value -0.9, using loaded terms like 'surveillance risks' and 'behavioral control'.
Leans toward support
DeepSeek leans support (0.12) and balances its loaded terms between 'surveillance' and 'data protection'.
Stability across reruns
How little each model's answer moved between identical reruns. Models are stochastic, so consistency is itself a finding.
Common questions
Which model is most opposed to a national digital ID?
Grok is most opposed with a value of -0.9 (Strongly oppose) and 100% stability.
Did any model refuse to answer on this topic?
No model refused; all six models had a refusal rate of 0%.
Why does DeepSeek lean support while Grok strongly opposes?
DeepSeek's value is 0.12, citing both surveillance and data protection; Grok's -0.9 emphasizes surveillance risks and behavioral control.
Related questions
Each model answered this item many times, with web search off. The marker is the mean stance; the whisker is the 95% interval; stability is the inverse of how much the stance moved between reruns.
