worldbench/WorldLens

[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

45
/ 100
Emerging

WorldLens helps evaluate the true capabilities of AI models designed to simulate driving environments. It takes a driving world model as input and provides a comprehensive report across 24 dimensions, covering visual realism, geometric consistency, and functional reliability. Autonomous driving researchers and engineers can use this to understand how their models perform in real-world scenarios.

188 stars.

Use this if you are developing or testing AI models that generate realistic driving simulations and need a thorough, multi-faceted evaluation of their performance.

Not ideal if you are looking for a tool to train driving models or to generate synthetic data for general computer vision tasks unrelated to autonomous driving.

autonomous-driving driving-simulation AI-model-evaluation robotics-testing virtual-environment-validation
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 12 / 25

How are scores calculated?

Stars

188

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Jan 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/worldbench/WorldLens"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.