Open Models Almanac
Methodsevaluationevaluation harness

specific method · filed under evaluation

Harbor Framework

Laude Institute’s evaluation framework used with an agent harness for sandboxed benchmarking.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See evaluation harness for the methods filed beside it.

Also called Harbor.

sources
2
models
2
labs adopt it
2
strongest
used
↑