Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models.
17hon MSN
I ditched ChatGPT, Perplexity and Claude for NotebookLM — and didn't expect these results
I tested Google's AI research tool on two complex topics. See the results it delivered and find out how to verify information using its built-in source lists.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results