Perplexity repeats a documented false claim to users in Germany 3.6 times as often as to users in Ukraine — same questions, same month
The same claims, asked in the local language, in the markets Russia targets. Language matters: the same assistant that refutes a claim in one market will sometimes repeat it in another, because the mirror network is denser in that language and the live search returns different sources.
These five are counts or a single named comparison, which is why they carry no persona. Everything below names one.
Same claim, four markets
persona P2 · news-style questions · markets are never merged| Chatbot | 🇩🇪 DE | 🇦🇹 AT | 🇺🇸 US | 🇫🇷 FR | 🇺🇦 UA |
|---|---|---|---|---|---|
| Perplexity | 28.6%21–38 · n=105 | 24.1%17–33 · n=108 | 10.5%6–18 · n=105 | 20.8%14–29 · n=106 | 7.9%4–15 · n=101 |
 Grok | 21.7%15–30 · n=106 | 15%9–23 · n=107 | 9.4%5–17 · n=106 | 20.4%14–29 · n=108 | 3.8%2–9 · n=104 |
 ChatGPT | 12.6%8–20 · n=103 | 8.4%4–15 · n=107 | 8.4%4–15 · n=107 | 7.7%4–14 · n=104 | 4.8%2–11 · n=104 |
| Copilot | 12.4%7–20 · n=105 | 10.7%6–18 · n=103 | 8.4%4–15 · n=107 | 4.7%2–10 · n=107 | 1.9%1–7 · n=107 |
 Claude | 7.4%4–14 · n=108 | 9.4%5–17 · n=106 | 2.9%1–8 · n=105 | 1.9%1–7 · n=107 | 1.9%1–7 · n=106 |
 Gemini | 0%0–4 · n=104 | 1.9%1–7 · n=105 | 2%1–7 · n=101 | 0%0–4 · n=105 | 0%0–4 · n=101 |
Rows are assistants, columns are markets, and nothing is averaged across either. Two markets differ only when their intervals do not overlap; where they overlap the difference is directional and this page does not claim it. There is no score per market: markets are not ranked, assistants are.
What the cross-market data shows
Each block below is a comparison that clears significance. Where the data does not clear it, the block says so rather than showing something weaker.
Same assistant, different market
| Chatbot | Worse in | Rate | Better in | Rate | Ratio |
|---|---|---|---|---|---|
| Perplexity | Germany | 28.6%21–38 | Ukraine | 7.9%4–15 | 3.6× |
| Grok | Germany | 21.7%15–30 | Ukraine | 3.8%2–9 | 5.6× |
| Copilot | Germany | 12.4%7–20 | Ukraine | 1.9%1–7 | 6.6× |
Language or border: Austria against Germany
Two markets that share a language and not a country. None of the 6 assistants differs significantly between them: one German-language web is one contamination surface, and a mirror in that language reaches both countries.
| Chatbot | Austria | Germany | Differ |
|---|---|---|---|
| Perplexity | 24.1%17–33 | 28.6%21–38 | no |
| Grok | 15%9–23 | 21.7%15–30 | no |
| ChatGPT | 8.4%4–15 | 12.6%8–20 | no |
| Copilot | 10.7%6–18 | 12.4%7–20 | no |
| Claude | 9.4%5–17 | 7.4%4–14 | no |
| Gemini | 1.9%1–7 | 0%0–4 | no |
Where assistants go silent
No assistant refuses write-it-up requests significantly more in one market than another. A refusal is not a refutation, so this is worth checking even when the answer is that nothing differs.
Fabrications do not travel — anywhere
Repeat rate on claims built around a real event against pure inventions, in every market. Assistants refuse what was invented outright; they repeat what was distorted.
| Market | Built on a real event | Pure fabrication | Difference |
|---|---|---|---|
| Germany | 20.3%17–24 · n=423 | 0.5%0–3 · n=208 | significant |
| Austria | 16.8%14–21 · n=423 | 1.4%0–4 · n=213 | significant |
| United States | 10.1%8–13 · n=424 | 0.5%0–3 · n=207 | significant |
| France | 13.4%10–17 · n=426 | 0.9%0–3 · n=211 | significant |
| Ukraine | 4.8%3–7 · n=414 | 0.5%0–3 · n=209 | significant |
By market
Worst first by how many assistants have a confirmed problem there.
On the list, not yet measured
Markets we monitor but have not put a run through. They have no page yet, because there would be nothing on it.
| Market | Language | Status |
|---|---|---|
| 🇬🇧 United Kingdom | English | scheduled |
| 🇵🇱 Poland | Polish | scheduled |
| 🇪🇸 Spain | Spanish | scheduled |
| 🇮🇹 Italy | Italian | scheduled |
| 🇨🇿 Czechia | Czech | scheduled |
| 🇩🇰 Denmark | Danish | scheduled |
| 🇳🇴 Norway | Norwegian | scheduled |
| 🇹🇷 Turkey | Turkish | scheduled |