Human Creativity Benchmark - Desktop Apps (Refinement) - Usability: leaderboard

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

Top models

#ModelScore
1GPT-5.3 Codex3.86
2Claude Opus 4.63.77
3Qwen 3.5 397B A17B3.69
4Gemini 3.1 Pro (Preview)3.66

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