I ran a fuller round of benchmarks on my bespoke coding agent and a few on Kilo Code for comparison. I do have runs with non-Flash models as well. I didn't complete any full benchmarks for them as… | Josh Heitzman

log in to save, upvote or flag this.

─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

related read on: