maghzalmit
PathEval
A benchmark for evaluating Vision-Language Models as evaluators in complex path-planning scenarios, where VLMs must compare two paths and determine which better satisfies given optimization criteria.
Downloads101
Technical Profile
- Modalities
- rgb
- Environment
- simulation
- Task Types
- path_planningnavigation
- Data Format
- json
- License
- mit
Community Signals
Top 50% by downloads
Access
Need custom rgb data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack