kir-gadjello

I don't think it's strictly better than GLM 5, more like they are peers (but in math competitions StepFun is stronger than most), and in my experience have similar coding/bugfix ceiling where world knowledge is not the deciding factor. But I didn't test GLM 5 for more than 30 hours, and my agentic harness (opencode) might be suboptimal - I'm open to the idea that GLM 5 with the right agentic harness is ready for ultra-long autonomy, but I have yet to see it myself.

Where GLM 5 is strictly worse for me though, compared to StepFun, is long-form content generation (planning, research documents) - but this can be said about geminis too and these are obviously very smart models.

Given the free option I'd explore GLM 5 more, but if I had to pay for it myself ofc I'd choose stepfun every time. Basically I think right now the optimal configuration for maximizing output of correct software features per dollar involves using StepFun or its future class competitor for bulk coding and first stage code review.

Maybe I need to write a blogpost about it after all.

Much worse - from my experience minimax is not suitable for high autonomy on hard projects. The real distant second in my experience is mimo flash v2 (but I did not try the latest version, might be closer to parity). I would not use minimax for serious work.

StepFun 3.5 Flash is better compared to google's gemini 3 flash which is surprisingly good and pretty costly, and to GLM-5.

I find this outcome ironic given minimax's more aggressive marketing and large-scale distillation accusations from Anthropic specifically accusing minimax but not StepFun.

I can only wonder about the true underlying reasons, but deducing from public information I suspect that minimax simply has weaker, benchmaxx-targeting post-training R&D and leans more on distillation of western frontier models, while StepFun has extensive post-training with lots of hard-won custom R&D and internal large-scale distillation teachers.

Yeah, my github is in the profile. Soon (tm). Feel free to follow.

I use pi, but I'm almost done writing a better alternative that doesn't have pi's stability issues. 80K Rust SLOC and a few hundred tests btw.

I think we are at this point where the hard ceiling of a strong model is pretty hard to delineate reliably (at least in coding, in research work it's clearer ofc) - and in a good sense, meaning with suitable task decomposition or a test harness or a good abstraction you can make the model do what you thought it could not. StepFun is a strong model and I really enjoyed studying and comparing it to others by coding pretty complex projects semi-autonomously (will do a write up on this soon tm).

Even purely pragmatically, StepFun covers 95% of my research+SWE coding needs, and for the remaining 5% I can access the large frontier models. I was surprised StepFun is even decent at planning and research, so it is possible to get by with it and nothing else (1), but ofc for minmaxing the best frontier model is still the best planner (although the latest deepseek is surprisingly good too).

Finally we are at a point where there is a clear separation of labor between frontier & strong+fast models, but tbh shoehorning StepFun into this "strong+fast" category feels limiting, I think it has greater potential.

I just use openrouter, it's free for now. But I would pay 30-100$ to use it 24/7.

Synthetic data researchers, connoisseurs and artisans, obviously. Feedback loop architects. Mindscaping artists.