A multimodal design-to-code benchmark built from community Figma designs, integrating screenshots, structured metadata, and design assets. The dataset was created by xcodemind and last updated on April 29, 2026.
Use Cases
- Benchmarking multimodal AI models based on integrated screenshots and metadata.
- Training models for UI code generation based on real-world Figma design assets.
- Evaluating model performance on practical UI development scenarios beyond image-only inputs.
Strengths
- Integrates multiple modalities: UI screenshots, structured metadata, and design assets.
- Built from real-world community Figma designs, likely reflecting practical UI development scenarios.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Freshness should be verified as the last update date is April 29, 2026.
Provenance
- Source
- Community Figma designs.
- Collection Method
- Built from Figma designs and integrated assets.
- Freshness
- 2026-04-29 10:40:45