What caused the switch was that we're building AI solutions for sometimes price-conscious customers, so I was already familiar with the pattern of "Use a superior model for setting a standard, then fine-tuning a cheaper one to do that same work".
So I brought that into my own workflows (kind of) by using Opus 4.6 to do detailed planning and one 'exemplar' execution (with 'over documentation' of the choices), then after that, use Opus 4.6 only for planning, then "throw a load of MiniMax M2.5s at the problem".
They tend to do 90% of the job well, then I sometimes do a final pass with Opus 4.6 again to mop up any issues, this saves me a lot of tokens/money.
This pattern wasn't possible with Claude Code, thus my move to Open Code.
I’ve used M2.5 in OpenCode using their Zen inference. I found it to be decent. Did not really seem comparable to Opus 4.5 for "quality" output. As in, I often tweaked the output more when using M2.5.
I think the best thing was the speed. If it is going to be wrong, I would prefer it to be wrong quickly.
> Leanstral
> Our first open-source code agent designed for Lean 4, built for formal proof engineering in realistic repositories. 119B parameters with 6.5B active.
But crucially they used "--" and not "—" which means they're safe. Unless it's learning. I may still be peeved that my beloved em dash has been tainted. :(
reply