How 23 AI image models render: “Exactly six ripe pears sit on a pale stone counter: two green pears on the left, two yellow pears in the center, and two red pears on the right. A small blue plate sits above the center pair, nothing else.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: every stated element present, correct count, correct placement. 179 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-06
Checklist: 6 ripe pears · 2 green pears on the left · 2 yellow pears in the center · 2 red pears on the right · small blue plate above the center pair · nothing else
23 text-to-image models rendered this prompt adherence prompt with the identical text at their default settings and a fixed seed. Krea 2 Large is the community favourite so far, winning 72% of its 18 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.2s.
What to look for: the right count of objects, the right spatial relationships, the stated colours and attributes, and nothing added.
- Krea 2 Large72%Krea29.8s · 80 cr Try
- GPT Image 2.5 Sunburst71%OpenAI26.1s · 40 cr Try
- FLUX 3 Image67%Black Forest Labs18.5s · 32 cr Try
- Nano Banana 2 Lite61%Google13.2s · 36 cr Try
- 5.2s · 80 cr Try
- Muse Image 1.058%Meta17.8s · 12 cr Try
- Kling v3 Omni50%Kuaishou48.6s · 35 cr Try
- Qwen Image 3.0 Pro50%Alibaba26.3s · 36 cr Try
- Qwen Image 3.042%Alibaba7.4s · 32 cr Try
- Seedream 5.0 Pro41%ByteDance32.7s · 49 cr Try
- Recraft v4 Pro36%Recraft · retired from voting18.9s · 300 cr Try
- ImagineArt 235%ImagineArt94.2s · 60 cr Try
- Krea 2 Medium35%Krea31.1s · 40 cr Try
- ImagineArt 1.5 Pro33%ImagineArt54.0s · 55 cr Try
- Ideogram v432%Ideogram10.7s · 40 cr Try
- Seedream 5.0 Flash29%ByteDance29.3s · 22 cr Try
- Ideogram v4.529%Ideogram14.2s · 80 cr Try
- 25%16.7s · 50 cr Try
- GPT Image 2.5 Flare25%OpenAI31.6s · 40 cr Try
- Recraft v417%Recraft · retired from voting11.1s · 45 cr Try
- GPT Image 27%OpenAI52.5s · 60 cr Try
- Midjourney Niji 7Midjourney · retired from voting134.3s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- Krea 2 Large leads this prompt in the BudgetPixel AI Image Arena, winning 72% of its 18 blind head-to-head votes. Vote on the arena page to add your judgement.
- Were the prompts adjusted per model?
- No. Every model received the exact same prompt, unmodified, at its default settings, with no negative prompt or style suffix. Some models rewrite prompts internally, and that is part of what is being compared.
- Can I run this prompt myself?
- Yes. Each tile’s “Try” link opens the BudgetPixel workshop with this prompt and that model preselected.