CRBench is a method-agnostic benchmark for long-context LLMs that measures contextual capability retained relative to a dense reference alongside memory and system resource efficiency.
-
Updated
Aug 28, 2026 - Python
#
resource-aware-evaluation
Here is 1 public repository matching this topic...
Improve this page
Add a description, image, and links to the resource-aware-evaluation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the resource-aware-evaluation topic, visit your repo's landing page and select "manage topics."