Benchmarking

[olimorris]

Hi Community,

I wondered if any of you had any recommendations for potential coding benchmarks that I could begin to test CodeCompanion (with certain models and tools) against?

I'm looking at completely redoing the workflow feature in the plugin (I think it's actually stopped working 😆) now that we have tools in a good place. But...I'd like to begin comparing how well it performs against some specific benchmarks.