Added Qwen3 Next to the Brokk Power Ranking Open Round (coding benchmark). It's roughly GPT-OSS-20b strength.

noahbp 4 days ago | parent | next [-]

Is that the updated Kimi K2, or the old Kimi k2?

	▲	jbellis 4 days ago \| parent [-]
		It's the original. I'll update the label to clarify.

This would be a valuable benchmark if it included languages other than Java, and let me see which models are best at the languages I work with.

My real-world usage does not line up with these results, but I'm not working with Java.