Only 3.2 Percent of Recommendations Are Unanimous
Unanimous agreement across ChatGPT, Claude, and Gemini is rare. When all three engines were asked the same buyer question, they all named the same company just 3.2 percent of the time.
3.2 percent
The finding
Of 56819 company-question pairs where at least one engine made a recommendation, only 1812 pairs (3.2 percent) were named by all three engines.
Unanimous agreement is the rarest outcome. Partial agreement (two engines agreeing) is more common at 8.4 percent, but still unusual. The dominant pattern is sole mention at 88.4 percent.
The distribution of agreement
| Engines naming the company | Pairs | Percent |
|---|---|---|
| 1 (sole mention) | 50209 | 88.4 |
| 2 (partial agreement) | 4798 | 8.4 |
| 3 (unanimous) | 1812 | 3.2 |
The distribution is heavily skewed toward disagreement. This is not a world where engines mostly agree with occasional differences; it is a world where engines mostly differ with occasional agreement.
What unanimous agreement signals
A company that achieves unanimous recommendation for a question has crossed a high bar. Something about that company made all three engines, with their different training data, different retrieval systems, and different reasoning processes, independently conclude it was worth naming.
Possible drivers of unanimous agreement:
- Dominant market position. A company so well-known in its category that all engines have strong signals about it.
- Broad information presence. The company appears in sources that all three engines draw from, not just sources one engine favors.
- Unambiguous category fit. The company clearly belongs in the answer to this specific question, with no reasonable argument for excluding it.
What this means for visibility tracking
The rarity of unanimous agreement means that "AI visibility" is not a single number. A company might be highly visible on one engine and invisible on two. Aggregating these into a single score obscures more than it reveals.
A meaningful visibility metric should report per-engine results separately, allowing companies to see where they are strong and where they have gaps.
What this means for buyers
Buyers relying on a single AI assistant are seeing that assistant's perspective, not a market consensus. For high-stakes decisions, checking multiple assistants may reveal options that one alone would not surface.
The 3.2 percent unanimous rate suggests that the recommendations a buyer receives are mostly unique to their chosen assistant.
Study context
The study examined 2500 prompts across 3 engines and 30564 companies. Unanimous agreement was calculated as the share of company-question pairs where all three engines named the same company, out of all pairs where at least one engine made a recommendation.
Other findings
How often does only one AI engine recommend a company when other engines do not?
The Sole-Mention Rate: Why Most AI Recommendations Are Unique to One Engine
When an AI engine recommends a company for a buyer question, that recommendation is unique to that engine 88.4 percent of the time. The other two engines simply do not mention the same company.
Which AI engine recommends the most companies?
ChatGPT Recommends More Companies Than Claude or Gemini
ChatGPT mentioned 42.7 percent of the companies studied, compared to 39.9 percent for Claude and 33.6 percent for Gemini. The engines have different thresholds for recommendation.
Do AI engines agree more on certain types of buyer questions?
Query Type Does Not Predict Engine Agreement
Whether a prompt is transactional, informational, or navigational, engines agree at roughly the same rate. Appearance rates range only from 36.9 to 38.6 percent.
Want to know how AI answers describe you?
We run the same measurement on your category. Fifteen minutes with founder Omar Jenblat, your own numbers, no deck.