Compact SUVs
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%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (25%)
- deepseek/deepseek-v4.1-flash @ deepseek-v4.1-flash via OpenRouter (25%)
Too closeNo single favourite: Mazda and Toyota share the top tier for these 4 API models.
Tier 1
- Toyota81%95% interval 72–89%plausible rank 1–2
- Mazda67%95% interval 57–77%plausible rank 1–4
Tier 2
- Honda37%95% interval 26–48%plausible rank 2–9
- Subaru33%95% interval 22–44%plausible rank 2–9
- Nissan14%95% interval 7–25%plausible rank 3–11
- Hyundai12%95% interval 5–21%plausible rank 3–11
- Kia10%95% interval 4–19%plausible rank 3–11
- Volkswagen9%95% interval 3–18%plausible rank 3–11
- Ford6%95% interval 1–15%plausible rank 3–11
Tier 3
- BMW3%95% interval 0–10%plausible rank 5–11
- Chevrolet1%95% interval 0–5%plausible rank 5–11
Drag across the chart to probe a share.
Too closeNo single favourite: Mazda and Toyota share the top tier for these 4 API models.
| Brand | Choice share | 95% interval | Plausible rank | Tier |
|---|---|---|---|---|
| Toyota | 81% | 72–89% | 1–2 | Tier 1 |
| Mazda | 67% | 57–77% | 1–4 | Tier 1 |
| Honda | 37% | 26–48% | 2–9 | Tier 2 |
| Subaru | 33% | 22–44% | 2–9 | Tier 2 |
| Nissan | 14% | 7–25% | 3–11 | Tier 2 |
| Hyundai | 12% | 5–21% | 3–11 | Tier 2 |
| Kia | 10% | 4–19% | 3–11 | Tier 2 |
| Volkswagen | 9% | 3–18% | 3–11 | Tier 2 |
| Ford | 6% | 1–15% | 3–11 | Tier 2 |
| BMW | 3% | 0–10% | 5–11 | Tier 3 |
| Chevrolet | 1% | 0–5% | 5–11 | 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.
- Models chose on EPA specification facts only; purchase price, reliability and availability were not assessed.
- 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 in randomized shortlists of 4 (chance is 25%). In each scenario, every brand in the shortlist is shown by its catalog configuration that best fits that shopper's stated requirements (never by price or any commercial data), so a brand's share measures how its best-fitting configuration competes — not an average over all its trims or sales. 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%)
- mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (25%)
- deepseek/deepseek-v4.1-flash @ deepseek-v4.1-flash 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).