Cruise lines
Which brand 5 AI models pick, with intervals.
Fast panel · Panel, equal weight
- anthropic/claude-haiku-5.5 @ claude-haiku-5.5 via OpenRouter (20%)
- openai/gpt-6-luna @ gpt-6-luna via OpenRouter (20%)
- google/gemini-4-argon @ gemini-4-argon via OpenRouter (20%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (20%)
- deepseek/deepseek-v4.1-flash @ deepseek-v4.1-flash via OpenRouter (20%)
Too closeNo single favourite: Azamara Cruises, Crystal, Norwegian Cruise Line, Viking, Virgin Voyages, and Windstar Cruises share the top tier for these 5 API models.
Tier 1
- Azamara Cruises53%95% interval 40–65%plausible rank 1–6
- Crystal51%95% interval 39–63%plausible rank 1–6
- Viking49%95% interval 39–59%plausible rank 1–6
- Norwegian Cruise Line31%95% interval 20–43%plausible rank 1–8
- Virgin Voyages27%95% interval 17–39%plausible rank 1–8
- Windstar Cruises26%95% interval 17–37%plausible rank 1–8
Tier 2
- Royal Caribbean19%95% interval 10–29%plausible rank 4–11
- Carnival Cruise Line8%95% interval 2–19%plausible rank 4–11
- MSC Cruises6%95% interval 2–12%plausible rank 7–11
- Disney Cruise Line4%95% interval 0–13%plausible rank 7–11
- Margaritaville at Sea1%95% interval 0–10%plausible rank 7–11
Drag across the chart to probe a share.
Too closeNo single favourite: Azamara Cruises, Crystal, Norwegian Cruise Line, Viking, Virgin Voyages, and Windstar Cruises share the top tier for these 5 API models.
| Brand | Choice share | 95% interval | Plausible rank | Tier |
|---|---|---|---|---|
| Azamara Cruises | 53% | 40–65% | 1–6 | Tier 1 |
| Crystal | 51% | 39–63% | 1–6 | Tier 1 |
| Viking | 49% | 39–59% | 1–6 | Tier 1 |
| Norwegian Cruise Line | 31% | 20–43% | 1–8 | Tier 1 |
| Virgin Voyages | 27% | 17–39% | 1–8 | Tier 1 |
| Windstar Cruises | 26% | 17–37% | 1–8 | Tier 1 |
| Royal Caribbean | 19% | 10–29% | 4–11 | Tier 2 |
| Carnival Cruise Line | 8% | 2–19% | 4–11 | Tier 2 |
| MSC Cruises | 6% | 2–12% | 7–11 | Tier 2 |
| Disney Cruise Line | 4% | 0–13% | 7–11 | Tier 2 |
| Margaritaville at Sea | 1% | 0–10% | 7–11 | Tier 2 |
How to read this
- Choice share: how often models pick a brand when it appears in a shortlist of 4. Chance is 25%, the dashed line.
- The band is the 95% interval; the bright tick is the estimate. Overlapping bands are not a strict order.
- Tiers are published: a tier groups brands not distinguishable from that tier's leader. Same tier does not mean equal.
- Rank shows the plausible rank range, not a strict place.
- Drag across the chart to probe a share and see which intervals contain it.
- Brand names only: the models saw each option as a brand name, with no product facts, and answered from their own knowledge.
- Fast panel: the fast or small current models of each vendor, not the full flagship panel.
- Each page shows the latest edition. Dates are in the downloadable JSON.
Panel and conditions
Each edition puts the brands of the category to a panel of AI models, called through their APIs, in randomized shortlists of 4 (chance is 25%). Each option was a brand name only, with no product facts, prices or any commercial data, so a brand's share measures which brand the models recommend from their own knowledge for the shopper needs of the scenarios. Shares come with 95% intervals; tiers and rank intervals are simultaneous at the same level.
- anthropic/claude-haiku-5.5 @ claude-haiku-5.5 via OpenRouter (20%)
- openai/gpt-6-luna @ gpt-6-luna via OpenRouter (20%)
- google/gemini-4-argon @ gemini-4-argon via OpenRouter (20%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (20%)
- deepseek/deepseek-v4.1-flash @ deepseek-v4.1-flash via OpenRouter (20%)
Conditions: closed-book API calls via OpenRouter (pinned providers); web search, grounding, tools and retrieval off; forced choice; 2 paraphrases per scenario in English.
Methodology: ACM-1.0-chart-draft (draft rules for movement, significance and events, awaiting review).