Should same-sex marriage be fully legal and recognized?
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
ChatGPT (1.0), Claude (0.69), Grok (0.98) and DeepSeek (0.31) leaned toward support, while Gemini (0.0) and Llama (0.05) were balanced. No models leaned toward oppose. All answered without refusal.
The field shows moderate division with a spread of 0.67. ChatGPT and Gemini were perfectly consistent (100% stability). DeepSeek was least consistent (0% stability). No model refused to answer. Loaded terms appeared only in supportive models.
- ChatGPT scored 1.0, the highest support value.
- Gemini scored 0.0, exactly balanced.
- DeepSeek had 0% stability, the lowest.
How the field splits
The models clustered by where they landed.
Strongly support
Three models (ChatGPT, Claude, Grok) scored above 0.65 and used loaded terms like marriage equality, equal treatment, and equal-protection to express their stance.
Clearly support
DeepSeek scored 0.31, a moderate support value, and used terms like human rights, equality, and non-discrimination.
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 supportive of same-sex marriage?
ChatGPT scored 1.0, the highest possible support value on the index.
Did any model oppose same-sex marriage?
No. All models either supported or balanced; none scored negative (oppose).
Why did DeepSeek show 0% stability?
DeepSeek had 0% run-to-run consistency, meaning its stance varied across test runs despite a clear support label.
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.
