Four AI engines, four different Christmas shopping recommendation leaders
Research spanning more than 330,000 AI visibility data points reveals different recommendation leaders across four engine-labelled samples, including Fortnum & Mason, Space NK, Cult Beauty and John Lewis.
Research from Citations.io's AI Advent Calendar Index 2026, examining more than 330,000 recorded AI visibility data points across four engine-labelled samples, reveals how AI engines represented and recommended brands and retailers in sampled UK shopping questions for Christmas 2026.
Four engine groups, four different recommendation leaders
The general Christmas and gift calendar questions produced different leading extracted brands in each engine group:
- ChatGPT-labelled sample: Fortnum & Mason — 43.8% visibility, 43.8% recommendation rate, 100% positive classified sentiment.
- Claude-labelled sample: Space NK — 67.7% visibility, 60.8% recommendation rate, 89.8% positive sentiment.
- Gemini-labelled sample: Cult Beauty — 42.2% visibility, 39.8% recommendation rate, 94.4% positive sentiment.
- Perplexity-labelled sample: John Lewis — 58.5% visibility, 54.6% recommendation rate, 89.5% positive sentiment.
How the shortlists differ
Within the ChatGPT-labelled sample, John Lewis achieved a 40.0% recommendation rate and Hotel Chocolat 38.5%. In the Claude-labelled sample, Cult Beauty followed Space NK at 59.2%, with Boots at 48.5%. Gemini's next most recommended names were Fortnum & Mason (32.8%) and Boots (28.9%). Perplexity's were Boots (50.0%) and Space NK (40.0%).
The leading brands all recorded overwhelmingly positive classified sentiment in their own groups, but a positive mention is not proof of a better calendar or a satisfied shopper. Across the full study, 64.0% of classified brand mentions were positive, 35.9% neutral and 0.1% negative. The overwhelmingly non-negative tone reflects a shopping recommendation task and the automated sentiment extraction process; it should not be interpreted as consumer satisfaction.
Why the engine matters
The samples reflect model/API observations, rather than controlled tests of today's consumer interfaces or live browsing and personalisation features. They do not establish which AI assistant gives better shopping advice. They do illustrate that the brands recommended by one model group need not be the same as those recommended by another.
Read the full AI Advent Calendar Index 2026.
Methodology and limitations
Study scale: 334,830 recorded data points comprising 79,541 brand mention records, 79,541 recommendation classifications, 79,532 sentiment classifications, 39,777 non-null answer position measurements and 56,439 extracted source reference records. URL and domain representations of a source are not counted separately. These data points are measured attributes of sampled AI responses, not independent observations. The collection period is documented in the full study methodology. Source references are extracted and are not necessarily verified or native citations.
Analysis: The findings use saved neutral-market prompts explicitly referencing 2026, excluding purchase-location and availability intent. The comparison uses the stored engine-labelled model/API groups for ChatGPT (OpenAI GPT-5 mini), Claude, Perplexity and Gemini. AI visibility is the percentage of relevant answers containing a brand mention; recommendation rate is the percentage containing a brand flagged as recommended. Both use distinct answers and stored canonical brand labels, excluding flagged off-topic records. Positive, neutral and negative sentiment are percentages of classified brand mentions; unknown labels are excluded. Sentiment is automated interpretation of generated text, not human consumer sentiment, and may correlate with the recommendation classifier. Multiple brands can appear per answer, and category subsets overlap. The study is not weighted to actual shopper behaviour.
The figures describe a preliminary historical sample; extraction and alias matching can introduce errors. The study does not provide live rankings or verify current product availability, price, quality or sales. The overall data point count describes the full study, not the denominator of each headline. Repeated answers to the same question are not independent; close rankings and smaller subsets are directional. Exact sample sizes and category denominators are available on request for editorial or research verification.
Media enquiries
Citations.io is an AI citation intelligence platform helping brands understand how AI engines mention, rank and cite them. For research enquiries, supporting data or commentary, contact Josh Tulip, founder, at support@citations.io.
AI Advent Calendar Index 2026
Leading brand in each engine-labelled sample: visibility and recommendations
Sampled AI visibility and recommendation rate for the selected names in the source brief. These are distinct measures, not product-quality scores.
Fortnum & Mason
ChatGPT-labelled sample
Positive classified sentiment: 100.0%. Other sentiment shares are not stated in this brief.
Space NK
Claude-labelled sample
Positive classified sentiment: 89.8%. Other sentiment shares are not stated in this brief.
Cult Beauty
Gemini-labelled sample
Positive classified sentiment: 94.4%. Other sentiment shares are not stated in this brief.
John Lewis
Perplexity-labelled sample
Positive classified sentiment: 89.5%. Other sentiment shares are not stated in this brief.
Sentiment describes classified brand mentions in sampled AI output, not customer satisfaction. Unknown labels are excluded. Category and engine samples have their own denominators and are not directly interchangeable.
Related briefs
- Fortnum & Mason leads AI's general advent calendar recommendations for Christmas 2026
- Selfridges leads sampled AI recommendations for luxury beauty advent calendars
- LEGO leads AI's children's advent calendar recommendations in UK study
- Hotel Chocolat leads AI's chocolate advent calendar recommendations
- John Lewis leads AI retailer visibility across Christmas advent calendar categories
- AI Advent Calendar Index 2026: the brands AI recommends to UK shoppers
- Boots leads AI beauty advent calendar recommendations in UK Christmas study
- Superdrug and Boots dominate sampled AI budget beauty advent calendar recommendations
- Jo Malone London and Diptyque share the lead in AI home and fragrance calendar recommendations
- Monica Vinader and Pandora lead sampled AI jewellery calendar recommendations

