PROJECT / First-party project
kine-bench
Evaluation and evidence gating for claims about world-model planning.
01 / Overview
kine-bench
Evaluation and evidence gating for claims about world-model planning.
02 / Research question
Research question
How can capability claims map to clear tests and failure boundaries?
03 / Approach
Approach
Develop inspectable evaluation interfaces and evidence records.
04 / Architecture and scope
Architecture and scope
Consult repository documentation and code for exact architecture and interfaces. This page describes only the public research scope.
05 / Current stage
Research tooling
06 / Inspect the evidence
Inspect the evidence
View evidence ↗07 / Limitations
Limitations
An evaluation framework is not evidence that a model achieved a score.
08 / CODE
Repository
https://github.com/kineworld/kine-bench ↗09 / Next steps
Next steps
Follow new inspectable experiments and documentation in the repository.