Meal kits
Which brand 4 AI models pick, with intervals.
Fast panel · Panel, equal weight
- anthropic/claude-haiku-5.5 @ claude-haiku-5.5 via OpenRouter (25%)
- openai/gpt-6-luna @ gpt-6-luna via OpenRouter (25%)
- google/gemini-4-argon @ gemini-4-argon via OpenRouter (25%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (25%)
Too closeNo single favourite: Gobble, Green Chef, HelloFresh, Home Chef, Hungryroot, Marley Spoon, Purple Carrot, and Sunbasket share the top tier for these 4 API models.
Tier 1
- HelloFresh39%95% interval 25–54%plausible rank 1–8
- Sunbasket38%95% interval 23–52%plausible rank 1–9
- Home Chef32%95% interval 19–46%plausible rank 1–9
- Hungryroot32%95% interval 20–46%plausible rank 1–9
- Purple Carrot24%95% interval 11–39%plausible rank 1–9
- Green Chef23%95% interval 11–37%plausible rank 1–9
- Marley Spoon22%95% interval 10–35%plausible rank 1–9
- Gobble15%95% interval 5–29%plausible rank 1–9
Tier 2
- EveryPlate12%95% interval 2–27%plausible rank 2–9
Drag across the chart to probe a share.
Measured but left off the chart
- Blue Apron: Too many planned scenarios would be left out
Too closeNo single favourite: Gobble, Green Chef, HelloFresh, Home Chef, Hungryroot, Marley Spoon, Purple Carrot, and Sunbasket share the top tier for these 4 API models.
| Brand | Choice share | 95% interval | Plausible rank | Tier |
|---|---|---|---|---|
| HelloFresh | 39% | 25–54% | 1–8 | Tier 1 |
| Sunbasket | 38% | 23–52% | 1–9 | Tier 1 |
| Home Chef | 32% | 19–46% | 1–9 | Tier 1 |
| Hungryroot | 32% | 20–46% | 1–9 | Tier 1 |
| Purple Carrot | 24% | 11–39% | 1–9 | Tier 1 |
| Green Chef | 23% | 11–37% | 1–9 | Tier 1 |
| Marley Spoon | 22% | 10–35% | 1–9 | Tier 1 |
| Gobble | 15% | 5–29% | 1–9 | Tier 1 |
| EveryPlate | 12% | 2–27% | 2–9 | 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.
- Beta: intervals are not yet small-sample calibrated.
- 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 (25%)
- openai/gpt-6-luna @ gpt-6-luna via OpenRouter (25%)
- google/gemini-4-argon @ gemini-4-argon via OpenRouter (25%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (25%)
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).