HOT RADAR
llmHEAT 20.6°

AI CLUSTERED EVENT · 10/15/2026

Kombai Launches Design Creativity Bench: GPT-6 Astra Scores 65.5 vs Human 92.3 on UI Originality

1 reports archived1 independent sourcesupdated 10/15/2026, 00:33:34
Synthesis & Latest Updates
1 Sources Cross-Validated

Kombai introduces Design Creativity Bench, evaluating AI creativity in UI design across originality, creative range, and appropriateness. Results reveal a significant gap between frontier models and human designers, with the top model GPT-6 Astra scoring 65.5 against a human reference of 92.3. The benchmark's methodology and datasets are open-sourced to make design creativity a measurable dimension of model capability.

LATEST/Kombai introduces Design Creativity Bench, evaluating AI creativity in UI design across originality, creative range, and appropriateness. Results reveal a significant gap between frontier models and human designers, with the top model GPT-6 Astra scoring 65.5 against a human reference of 92.3. The benchmark's methodology and datasets are open-sourced to make design creativity a measurable dimension of model capability.

HEAT TRENDHourly heat curve

3 fully observed hours
Now
20.6
Peak
21.301:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. Hacker News AIT2·68 pts
    • Moves beyond single-metric quality checks by introducing Originality, Creative Range, and Appropriateness dimensions.
    • Top-performing model GPT-6 Astra scores 65.5, significantly trailing the human designer reference score of 92.3.
    • Reveals that while models generate functional UIs, they struggle with adaptive creative decisions across different product domains.
Kombai Launches Design Creativity Bench: GPT-6 Astra Scores 65.5 vs Human 92.3 on UI Originality | Today for AI