AI models
Which engines Noma tracks, choosing them, and why their answers differ.
Which AI models does Noma track?
Noma tracks 13 AI engines: ChatGPT, Gemini, Perplexity and Claude on every plan, and Grok, GPT-5, Claude Sonnet, DeepSeek, Qwen, Mistral Small, Mistral Medium, Google AI Mode and Google AI Overviews as add-ons. Each is polled daily on the same prompt set and reported separately rather than averaged, so they can be compared directly.
Can I choose which models to track?
Yes, under Settings, Engines. Turning an engine off stops new runs against it; the history already collected stays and remains visible in past periods.
Why do some AI answers include no sources?
Not every engine cites on every answer. Some answer from what they already know rather than retrieving pages, and those answers carry no citation list. Perplexity cites most consistently, which is why citation rate is tracked separately from mention rate.
Why do the AI engines disagree about my brand?
They read different sources and weigh them differently, so a brand can be prominent on one and absent on another. That disagreement is the reason Noma tracks them separately rather than as one blended score.