Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Xiaomi Mimo 2.6 live post-training dashboard

mimo.xiaomi.com

Post reply on HN
Print view View original

11–20 of 150 posts

Re: Xiaomi Mimo 2.6 live post-training dashboard

#11

Post by joelwallis »

I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve.

The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late last year/early this year). I'm fully invested in MiMo and I'm very happy with it.

-- PS: I also check almost daily to see if other models are capable of doing such great work. And they do – DS4F is powerful and DS41 is impressive, GLM 5.3 Flash gets a job done well, etc. – but when I add cost of M-token in the ROI math, Jeez! MiMo is an order of magnitude better.

Re: Xiaomi Mimo 2.6 live post-training dashboard

#12

Post by kibae »

krm01 wrote: post #3

This is pretty neat. What would be a good reason for the other Model providers to not do this?

Speculating here, but I assume researchers can make a reasonable estimate of the size of closed models based on factors like training time, training speed, and the number of tokens processed.

Also, Anthropic and OpenAI probably want to keep each other on their toes so they don’t end up on the wrong side of another Opus 4.6 / GPT-5.3-Codex situation, where one lab releases a model only for the other to drop a better one hours later.

Re: Xiaomi Mimo 2.6 live post-training dashboard

#13

Post by lucrbvi »

liuliu wrote: post #7

When you run benchmarks while training, isn't that the definition of contamination? Asking because I am not sure if this is normal in big labs now.

They are using it to evaluate checkpoints during the training, they are probably not using the benchmarks for training the models. It's a common practice for big reinforcement learning runs.

Re: Xiaomi Mimo 2.6 live post-training dashboard

#15

Post by james2doyle »

joelwallis wrote: post #11

I been using MiMo-V2.5 to do most of my work as software engineer, on a variety of projects I'm working on, and I been VERY happy with ROI. The model is very powerful! Not perfect – I've run in hallucination loops once or twice, but nothing a stop-then-continue wouldn't solve. The cost is unbelievably low, and the quality of intelligence I get is equivalent to when I was working mostly with Anthropic models (late las…

2.5 Pro or the regular 2.5?

I always found that those Mimo models to be really good at tool calling and following instructions

Re: Xiaomi Mimo 2.6 live post-training dashboard

#16

Post by GaggiX »

ProfessorLayton wrote: post #8

2.6 Pro: >started 2026-09-15 10:32 UTC For some reason I thought training took much, much longer than what the progress bar suggests. This is really neat, I'm currently using mimo 2.5 pro, and it's decent (or great given the price). Hopefully their next one is multimodal.

These are post-training reinforcement learning steps.

Re: Xiaomi Mimo 2.6 live post-training dashboard

#17

Post by bayindirh »

rozab wrote: post #6

Why are they doing this? To try head off accusations about distillation?

Sometimes you're confident about what you're doing and show how you work to the world.

Keeping the garage door open, or at least making the door translucent. It's always cool.

Re: Xiaomi Mimo 2.6 live post-training dashboard

#18

Post by jampekka »

liuliu wrote: post #7

When you run benchmarks while training, isn't that the definition of contamination? Asking because I am not sure if this is normal in big labs now.

Kinda yes. The benchmarks become part of the validation set, which means the models get slightly overfit to them if they are used as criteria for stopping the training. But a lot less compared to using them in the training data.

I'd guess everybody uses at least some benchmarks as stopping criteria, which is kinda sensible, but it also does induce some benchmaxxing, and explains partly why the newest models always tend to eke out in benchmarks.

https://en.wikipedia.org/wiki/Training,_validation,_and_test...

Re: Xiaomi Mimo 2.6 live post-training dashboard

#20

Post by krackers »

GaggiX wrote: post #16
ProfessorLayton wrote: post #8

2.6 Pro: >started 2026-09-15 10:32 UTC For some reason I thought training took much, much longer than what the progress bar suggests. This is really neat, I'm currently using mimo 2.5 pro, and it's decent (or great given the price). Hopefully their next one is multimodal.

These are post-training reinforcement learning steps.

Yes, updated the submission title to say "post-training" to hopefully prevent further confusion
Post reply on HN