Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models.

This proposal is complete and already merged into ECMA262 specification. See the specification text here. Thanks for help and feedback on this effort from Brendan Eich, Waldemar Horwat, Jaro Sevcik, ...

For legal stuff, see LICENSE. Basically, you may do whatever you want with the source. Use, modify, sell, print it out, roll it and smoke it - as long as I won't be held responsible.