Pickbench
Contact

Video game consoles

Which brand 10 AI models pick, with intervals.

60 scenariosBrand names only

Panel, equal weight

  • anthropic/claude-opus-5.5 @ claude-opus-5.5 via OpenRouter (10%)
  • openai/gpt-6.1-sol @ gpt-6.1-sol via OpenRouter (10%)
  • google/gemini-4-argon @ gemini-4-argon via OpenRouter (10%)
  • deepseek/deepseek-v4-pro @ deepseek-v4-pro via OpenRouter (10%)
  • mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (10%)
  • meta-llama/llama-4-maverick-17b-128e-instruct @ llama-4-maverick-17b-128e-instruct via OpenRouter (10%)
  • moonshotai/kimi-k3.1-pro @ kimi-k3.1-pro via OpenRouter (10%)
  • z-ai/glm-5.3 @ glm-5.3 via OpenRouter (10%)
  • qwen/qwen3.8-max-prime @ qwen3.8-max-prime via OpenRouter (10%)
  • x-ai/grok-4.7 @ grok-4.7 via OpenRouter (10%)

Too closeNo single favourite: Meta Quest, Nintendo, PlayStation, Valve, and Xbox share the top tier for these 10 API models.

Choice share · 95% interval
0255075100

Tier 1

  1. Xbox56%95% interval 43–69%plausible rank 1–5
  2. PlayStation49%95% interval 36–62%plausible rank 1–5
  3. Nintendo43%95% interval 30–56%plausible rank 1–6
  4. Valve35%95% interval 22–48%plausible rank 1–6
  5. Meta Quest17%95% interval 8–28%plausible rank 1–9

Tier 2

  1. ASUS ROG10%95% interval 4–19%plausible rank 3–9
  2. Lenovo Legion8%95% interval 3–16%plausible rank 5–9
  3. MSI5%95% interval 0–14%plausible rank 5–9
  4. AYANEO2%95% interval 0–7%plausible rank 5–9
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.
  • Flagship panel: one current flagship model per major vendor, plus the most-used models.
  • 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-opus-5.5 @ claude-opus-5.5 via OpenRouter (10%)
  • openai/gpt-6.1-sol @ gpt-6.1-sol via OpenRouter (10%)
  • google/gemini-4-argon @ gemini-4-argon via OpenRouter (10%)
  • deepseek/deepseek-v4-pro @ deepseek-v4-pro via OpenRouter (10%)
  • mistralai/mistral-large-4-0 @ mistral-large-4-0 via OpenRouter (10%)
  • meta-llama/llama-4-maverick-17b-128e-instruct @ llama-4-maverick-17b-128e-instruct via OpenRouter (10%)
  • moonshotai/kimi-k3.1-pro @ kimi-k3.1-pro via OpenRouter (10%)
  • z-ai/glm-5.3 @ glm-5.3 via OpenRouter (10%)
  • qwen/qwen3.8-max-prime @ qwen3.8-max-prime via OpenRouter (10%)
  • x-ai/grok-4.7 @ grok-4.7 via OpenRouter (10%)

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).

All boards