Skip to content

Evaluation & Quality

Model confidence score

A number showing how strongly an AI favors a particular prediction.

Example

AI gives one predicted group a score of 0.9.

Why people use it

It gives a numerical clue about how strongly AI favors one answer.

What you'll hear

“What does this 90% score mean?”

What this means for you

Ask what the number means before treating it as a 90% chance.

Can you control it?

No

No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.

Common questions

Does 0.9 always mean a 90% chance of being correct?
No. The service must explain the score and show that it matches real-world chances before that interpretation is justified.
Can the highest-scoring choice still be weak?
Yes. It may only be the best of several poor options.
Can scores from different systems be compared directly?
Not always. They may be calculated differently or mean different things.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice