How 22 AI image models render: “Across a brushed steel counter, exactly six fountain pens rest in three groups: two crimson pens on the left, two ivory pens in the center, and two cobalt pens on the right; 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. 126 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-16
Checklist: 6 fountain pens · 2 crimson pens on the left · 2 ivory pens in the center · 2 cobalt pens on the right · brushed steel counter · nothing else
22 text-to-image models rendered this prompt adherence prompt with the identical text at their default settings and a fixed seed. Kling v3 Omni is the community favourite so far, winning 75% of its 8 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.8s.
What to look for: the right count of objects, the right spatial relationships, the stated colours and attributes, and nothing added.
- Nano Banana 2 Lite75%Google24.0s · 36 cr Try
- Kling v3 Omni75%Kuaishou57.1s · 35 cr Try
- GPT Image 2.5 Flare73%OpenAI39.2s · 40 cr Try
- Seedream 5.0 Pro62%ByteDance34.8s · 49 cr Try
- Qwen Image 3.055%Alibaba7.3s · 32 cr Try
- Krea 2 Medium50%Krea14.8s · 40 cr Try
- GPT Image 2.5 Sunburst45%OpenAI50.1s · 40 cr Try
- FLUX 3 Image44%Black Forest Labs21.9s · 65 cr Try
- GPT Image 243%OpenAI · retired from voting49.4s · 60 cr Try
- Muse Image 1.040%Meta10.3s · 12 cr Try
- ImagineArt 236%ImagineArt · retired from voting24.0s · 60 cr Try
- Nano Banana 2.136%Google9.7s · 31 cr Try
- Krea 2 Large33%Krea29.1s · 80 cr Try
- Midjourney V8.233%Midjourney119.0s · 160 cr Try
- 29%13.4s · 50 cr Try
- Ideogram v427%Ideogram12.3s · 40 cr Try
- Seedream 5.0 Flash27%ByteDance20.7s · 22 cr Try
- Qwen Image 3.0 Pro27%Alibaba10.3s · 36 cr Try
- 4.8s · 80 cr Try
- Ideogram v4.518%Ideogram14.7s · 80 cr Try
- FLUX 3 Image KleinBlack Forest Labs6.4s · 12 cr Try
FAQ
- Which AI model renders this prompt best?
- Kling v3 Omni leads this prompt in the BudgetPixel AI Image Arena, winning 75% of its 8 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.