Updates

Benchmark releases, model additions, and methodology changes

Date

Type

Benchmark

Title

Link

2026-10-21

Release

Text-to-3D with LLM code

Text-to-3D with LLM code benchmark

View

2026-10-06

Release

World Models Realism v1

World Models Realism benchmark

View

2026-10-06

Release

Image-to-3D

Image-to-3D benchmark

View

2026-09-30

Release

Relative camera movement v1

Relative camera movement benchmark

View

2026-09-30

Release

World Model Physics v1

World Model Physics benchmark

View

2026-09-03

Release

Camera movement v1

Camera movement benchmark

View

2026-08-20

Release

SVG v1

SVG benchmark

View

2026-07-23

Release

Text-to-Image v1

Text-to-Image benchmark

View

We use crowd intelligence to deliver real, diverse human feedback at scale for model evaluation and post-training.

Benchmarks

Text-to-Image Camera Movement Relative Camera Movement Physics Realism Image-to-3D SVG LLM-to-3D Suggest a model or benchmark

Method

Methodology Data on Hugging Face

Rapidata

rapidata.ai Private benchmarks Contact X LinkedIn