Ask HN: Are MiniMax Models Scams?

3 points by XCSme 3mo ago ↗ HN

I kept trying to use their M2.5 model and now they released M2.7, but they are TERRIBLE.

See this comparison I made:

https://aibenchy.com/compare/minimax-minimax-m2-7-medium/minimax-minimax-m2-5-medium/z-ai-glm-5-medium/google-gemini-3-1-flash-lite-preview-medium/

Not only that, but M2.5 is #1 on OpenRouter, which is crazy: https://openrouter.ai/rankings

I think the only reason why it is #1 is because it is a scam. In the comparison you can see it had over 200k reasoning tokens, whereas most models have 20k-50k. Because OpenRouter ranks models based on usage, it does make sense M2.5 is on top, if it simply wastes tokens.

Did anyone actually use a MiniMax model and it actually worked? Are they simply benchmaxxed?

Is there a deeper conspiracy theory at play, or how can they keep releasing poor-performing models but people keep using then?

2 comments

[ 3.4 ms ] story [ 12.2 ms ] thread

james2doyle 3mo ago ↗

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.

dkersten 3mo ago ↗

> Did anyone actually use a MiniMax model and it actually worked?

Works well for me in Kilo Code. Its not as good as Opus, but its substantially cheaper and gets the job done. I don't have any problems with it.