Human Creativity Benchmark - Desktop Apps (Mockup) - Prompt Adherence: leaderboard

Metric: Mean expert Likert rating (1-5) of faithfulness to the prompt; desktop-app interfaces written as code at the Mockup stage, rated by professional creatives. Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.

Top models

#ModelScore
1Claude Opus 4.63.97
2GPT-5.3 Codex3.94
3Gemini 3.1 Pro (Preview)3.89
4Qwen 3.5 397B A17B3.63

Interactive version: theaggregate.ai/benchmark?slug=human-creativity-benchmark-desktop-apps-mockup-prompt-adherence · How It Works · Data refreshed daily, snapshot 2026-09-26.