Benchmarking code LLMs using user preference
arena.glaive.ai
Benchmarking code LLMs using user preference
1–2 of 2 posts
Re: Benchmarking code LLMs using user preference
#2This is neat. I feel like it should be blind by default though.
1–2 of 2 posts
Benchmarking code LLMs using user preference
arena.glaive.ai