Human Creativity Benchmark - Brand Assets (Mockup) - Prompt Adherence: leaderboard
Metric: Mean expert Likert rating (1-5) of faithfulness to the prompt; brand-design images at the Mockup stage, rated by professional creatives. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Nano Banana Pro (Gemini 3 Pro Image Preview) | 3.79 |
| 2 | GPT Image 1.5 | 3.54 |
| 3 | Seedream 4.5 | 2.92 |
| 4 | Flux 2 Max | 2.62 |
Interactive version: theaggregate.ai/benchmark?slug=human-creativity-benchmark-brand-assets-mockup-prompt-adherence · How It Works · Data refreshed daily, snapshot 2026-09-26.