I've been testing M3 for agentic tasks on Hermes and it just gets way too confused. I have really poor result from it compared to GPT-5.4 mini/regular or GLM-5.2 (and even 5.1).

▲

stevenhubertron 21 hours ago | parent [-]

This has been my experience as well to the letter.

	▲	ricardobeat 19 hours ago \| parent [-]
		M3 works best as a 'worker' agent. Create plans with a smarter model (Opus, K2.7, DeepSeek Pro) then use Minimax to execute.