Vibe Landing Page Arena: 36,000 Human Judgments on AI-Generated Web Designs

Vibe Landing Page Arena is a large-scale human preference dataset for evaluating AI-generated landing page design quality. It contains 36,000 pairwise judgments from 3,492 annotators comparing pages generated by four AI tools across 100 prompts and multiple design dimensions. The dataset was created by datapointai and last updated on Hugging Face in April 2026.

Use Cases

• Benchmarking AI-generated web design quality based on human preference judgments.
• Training or fine-tuning models for design evaluation based on pairwise comparison data.
• Analyzing the influence of design tones and business categories on user preference.
• Comparing the output quality of different AI code generation tools for web design.

Strengths

• 36,000 pairwise human judgments provide a substantial basis for analysis.
• Data covers 100 prompts, 97 business categories, and 82 design tones, suggesting diverse test conditions.
• Judgments were collected from 3,492 unique annotators, which may help mitigate individual rater bias.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file formats are unknown, which may limit suitability assessment.
• The dataset's freshness should be verified as the last update date is in the future (2026).

Provenance

Source

datapointai via Hugging Face.

Collection Method

Likely contains human judgments collected via a pairwise comparison platform or arena.

Time Range

null

Freshness

Last updated 2026-04-01 12:54:44; freshness should be verified.

Geography

null