Coffee
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: Blue Bottle Coffee, Counter Culture Coffee, La Colombe, Lavazza, and Peet's Coffee share the top tier for these 5 API models.
Tier 1
- Peet's Coffee56%95% interval 45–67%plausible rank 1–4
- Counter Culture Coffee46%95% interval 35–57%plausible rank 1–6
- Blue Bottle Coffee35%95% interval 23–47%plausible rank 1–8
- Lavazza33%95% interval 23–44%plausible rank 2–7
- La Colombe29%95% interval 19–40%plausible rank 1–9
Tier 2
- Starbucks21%95% interval 13–32%plausible rank 2–10
- Eight O'Clock Coffee19%95% interval 11–28%plausible rank 3–10
- Community Coffee12%95% interval 7–19%plausible rank 5–11
- Dunkin'12%95% interval 5–22%plausible rank 4–11
- Death Wish Coffee8%95% interval 2–18%plausible rank 6–11
Tier 3
- Folgers5%95% interval 1–11%plausible rank 8–11
Drag across the chart to probe a share.
Too closeNo single favourite: Blue Bottle Coffee, Counter Culture Coffee, La Colombe, Lavazza, and Peet's Coffee share the top tier for these 5 API models.
| Brand | Choice share | 95% interval | Plausible rank | Tier |
|---|---|---|---|---|
| Peet's Coffee | 56% | 45–67% | 1–4 | Tier 1 |
| Counter Culture Coffee | 46% | 35–57% | 1–6 | Tier 1 |
| Blue Bottle Coffee | 35% | 23–47% | 1–8 | Tier 1 |
| Lavazza | 33% | 23–44% | 2–7 | Tier 1 |
| La Colombe | 29% | 19–40% | 1–9 | Tier 1 |
| Starbucks | 21% | 13–32% | 2–10 | Tier 2 |
| Eight O'Clock Coffee | 19% | 11–28% | 3–10 | Tier 2 |
| Community Coffee | 12% | 7–19% | 5–11 | Tier 2 |
| Dunkin' | 12% | 5–22% | 4–11 | Tier 2 |
| Death Wish Coffee | 8% | 2–18% | 6–11 | Tier 2 |
| Folgers | 5% | 1–11% | 8–11 | Tier 3 |
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).