jev-as-judge Jev project
jev-as-judge is a Benchmarks and evals project built with Jev. Ten frozen refund traces in Akshay Pachaar's demo are code-checked, then Jev answers four
Ten frozen refund traces in Akshay Pachaar's demo are code-checked, then Jev answers four questions at once and the scores become Opik metrics.
Category: Benchmarks and evals. Built with Jev.
Author: Akshay Pachaar
More Jev projects are on Jev projects and apps. Related: Laya projects and apps.