Wikibench

Design2Code

coding

Multilingual: no

Design2Code evaluates the ability to generate code (HTML/CSS/JS) from visual designs.

Methodology

Imported from llm-stats public benchmark metadata. Modality: image. Max score: 100. Categories: code, multimodal, vision. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 2 of 2 results

  1. GLM-5V-Turbo self-reported llm-stats
    94.8%
  2. Qwen3 VL 235B A22B Thinking self-reported llm-stats
    93.4%