Microsoft Copilot locale variance tracking
Copilot locale behaviour follows Bing's market structure, so cross-market differences here mirror Bing's index differences more than any model-side variation.
How it renders
Controlled by egress country and language, following Bing's market handling.
Sampling
Each locale is its own sample set. A cross-market comparison at n=30 per market costs what it says on the tin, which is why we surface the arithmetic before you commit.
Gotcha
What the API returns
A single collection call against Microsoft Copilot for the locale variance field, sampled n times and returned as one object per prompt.
{
"engine": "copilot",
"field": "locale_variance",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"locales": [
{
"country": "GB",
"language": "en",
"share": 0.34,
"divergence": 0.02,
"unique_domains": 4
},
{
"country": "DE",
"language": "de",
"share": 0.19,
"divergence": 0.15,
"unique_domains": 11
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| country | string | ISO 3166-1 alpha-2 country of the egress used. |
| language | string | ISO 639-1 language the prompt was issued in. |
| share | float | Brand share within that locale. |
| divergence | float | Distance from the global mean for this prompt. |
| unique_domains | integer | Domains cited in this locale and nowhere else. |
What it costs
Each locale multiplies the collection count. Two markets at n=30 is 60 credits per prompt.
See credit pricing →Microsoft Copilot locale variance FAQ
- Why is Copilot weak in some markets?
- Bing index depth. Where Bing is thin, Copilot has less to cite.
- Which markets are worth running?
- Those where Bing has real share. We'll advise rather than sell you the full list.
Run Copilot only in markets where it means something
Tell us your countries and we'll tell you which ones are worth the credits.
Other Microsoft Copilot data
Across every engine
Compare how locale variance behaves on every engine we track.
Locale variance across all engines →