Xiaomi MiMo v2.6

(mimo.xiaomi.com)

152 points | by volf_ 54 minutes ago

19 comments

  • rao-v 33 minutes ago
    I know we have strong views on what a truly open model is (open weights, open training data, open training code etc.) but I really like how transparent they’ve been about the training of this model.

    The realtime dashboard they shared during training (https://mimo.xiaomi.com/rl/) was an incredible learning and teaching tool for me, and they’ve been unusually comprehensive in sharing details about their methodology (check out that tech report - it's got lots of clever behind the scene tricks like Google or Deepseek writeups) and benchmark scores (even the stuff they didn’t do well on).

    If you’re releasing an open model going forward, please consider offering the community more of this transparency!

    • earthnail 2 minutes ago
      Thanks so much for sharing this. As someone who mostly watches from the sideline, can you share what you can see in this dashboard that someone like me can't see? Is it the metrics themselves that they measure (the metrics tab is absurdly detailed), something in the notices, or something else I missed?
    • kingstnap 0 minutes ago
      [dead]
  • stymaar 30 minutes ago
    Flash[1]: 309B total / 15B activated parameters

    Pro [2]:, 1.02T total / 42B activated parameters

    [1]: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL

    [2]: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL

    • verdverm 13 minutes ago
      • gandreani 10 minutes ago
        Those this mean they've fine-tuned this Qwen 3.5 9B on output from the V2.6 model?
        • mydreamof 7 minutes ago
          It is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data
        • simonedepertis 6 minutes ago
          [flagged]
    • verdverm 19 minutes ago
      curious why the HF pill (on the right) always has inaccurate values
      • stymaar 11 minutes ago
        I noticed the same, and I wonder as well.
        • verdverm 3 minutes ago
          I suspect they are calculating something in the weights or config, I see it pretty consistently with quants
  • nemothekid 35 minutes ago
    Looking at the frontend design examples; why do these models seem to love the "01 - UPPERCASE TEXT" motif. It's everywhere now (see https://try.cloudflare.com/, which has '01 · QUICK TUNNELS', but no "02" anywhere).
    • danvayn 24 minutes ago
      My guess is that by function they break down frontend sections or components into pieces and I believe document things for themselves on some level, or purposely are verbose in this way. It is probably also shaped by users and existing web patterns. They probably get reinforced by models the more common they become.
    • sandblast 28 minutes ago
      Nice catch!
  • vatsachak 40 minutes ago
    Wow, the chinese labs are getting good at advertising model releases. The moat is thin.

    Some features of the release I like:

    - Demonstration of diverse tasks, such as using a DAW

    - Graphs from various benchmarks and price ranges

    - Real world use of the model in scientific environments

  • lwansbrough 11 minutes ago
    Anyone else more excited about Chinese models than American models these days? Big thing for me is affordability.
    • tacomagick 2 minutes ago
      Absolutely! Chinese models are both cheaper and more capable in many cases, compared to the American models and their makers continuously fumbling or reducing model capability with each update. Deepseek decreased costs when they released Flash 4.1 you would not see any American company do this, in reverse they would try charge you more.
    • swingandamiss 7 minutes ago
      No, because I'd rather not support our economic and military rivals.
      • lwansbrough 5 minutes ago
        I'm Canadian so this sentiment has little value in 2026 unfortunately.
      • Freedom2 6 minutes ago
        Agreed, and also because I support freedom of speech!
  • syntaxing 29 minutes ago
    All these new models are such tease for us folks with 128GB of shared memory. Buying another unit now to expand to 256GB is a mortgage payment but it’s getting tempting…
    • verdverm 13 minutes ago
    • brcmthrowaway 26 minutes ago
      Is there a gamechanger around the corner to reduce DRAM requirements?
      • zozbot234 6 minutes ago
        You could always stream from SSD storage. Especially effective if you get a cheap old-gen HEDT with lots of PCIe slots to add NVMe storage to and reasonable overall PCIe bandwidth.
      • stymaar 20 minutes ago
        n-gram per-layer embeddings[1][2] might be it.

        [1] https://sebastianraschka.com/llm-architecture-gallery/per-la...

        [2]: See DS 4.1-Flash and Qwen-3.8-Next.

        • verdverm 17 minutes ago
          this is to offload VRAM to DRAM (for GP comment), and makes no difference for URAM
          • zozbot234 1 minute ago
            You can definitely offload n-gram embeddings to storage; they're very sparsely used (only a few KB fetched per token) so this is quite effective. Loading to DRAM only becomes necessary if they are a bottleneck to overall performance (which might happen if you're doing very wide batches and everything else uses super fast VRAM/HBM).
          • stymaar 14 minutes ago
            Am I missing a joke? WTF is URAM?
            • verdverm 12 minutes ago
              unified memory, not sure if anyone uses URAM, I human hallucinated it
  • user43928 10 minutes ago
    I don't trust any of the benchmarks where Opus 5 surpasses Astra or Fable 5.1.

    Maybe Terminal Bench 4.0 and ExploitGym are reasonable.

    Terminal Bench 4.0

      GPT 6 Astra             59.6
      Claude Fable 5.1        55.1
      Claude Opus 5           49.0
      MiMo-V2.6-Pro           34.9
      MiMo-V2.6-Flash         28.8
      DeepSeek V4.1 Flash     26.8
      MiMo-V2.5-Pro            1.5
    
    ExploitGym

      GPT 6 Astra             42.4
      Claude Fable 5.1        30.4
      Claude Opus 5           22.1
      MiMo-V2.6-Pro           17.8
      MiMo-V2.6-Flash          6.0
      MiMo-V2.5-Pro            0.1
    
    DeepSWE v1.1

      DeepSeek V4.1 Flash     74.2
      Claude Opus 5           74.0
      GPT 6 Astra             74.0
      MiMo-V2.6-Pro           71.9
      Claude Fable 5          70.0
      MiMo-V2.6-Flash         67.9
      MiMo-V2.5-Pro           19.0
    • mokre 8 minutes ago
      Maybe you should not trust any of the benchmarks!
  • MisterMunchkin 18 minutes ago
    I really liked MiMo 2.5, it was really affordable and actually had vision, unlike DeepSeek. (DeepSeek has only recently added it)

    Just tried 2.6 flash on a really niche topic I specialise in and it has done a really good job. They’ve definitely polluted their training data with claudeslop, but looking past the slop there is a decent model.

    • omani 15 minutes ago
      how do you recognize "claudeslop"?
      • Bluestein 10 minutes ago
        It's an honest, load-bearing, simple thing.-
  • ddxv 36 minutes ago
    This looks great in terms of cost and capabilities, truly pushing the frontier forward in terms of open weight light weight models.
  • DanMcInerney 37 minutes ago
    This is a big week. Probably getting next OpenAI and Anthro models, Grok 4.7, Mimo, etc. These open source model releases are why I can't take the "slow down" crowd seriously. I pitted older Mimo, qwen, step, gpt-oss, and other models against each other playing games like Werewolf and Sketch.io-like games where I let them talk shit while they played against each other. Mimo was by far pareto frontier of game-playing for the models that were <$0.15/m input tokens on OpenRouter. Qwen was pareto frontier in the shit talking game though. Qwen's hilarious. https://www.tiktok.com/@clankerfights/video/7642862917582425...
  • algoth1 43 minutes ago
    Finally a lab that doesn't cheat on the charts
  • bertili 23 minutes ago
    They mixed up DeepSeek 4.1 Flash with something else on this page, possibly DeepSeek 4.1 Flash means Gemini 3.8 Flash.
  • NooneAtAll3 22 minutes ago
    does anyone know what unnamed model is on paretto frontier picture right between MiMo 2.5 and 2.6?

    so weird to acknowledge someone being on the front edge, but not name it

    • AnodicElegy 14 minutes ago
      Pretty sure that's Luna xhigh.
  • spwa4 20 minutes ago
    As for the stats that everyone wants:

    MiMo-V2.6-Flash-310B-A15B roughly GPT-5.6 Luna / Claude 4.9 according to benchmarks MiMo-V2.6-Pro-1.02T-A42B roughly GPT-5.6 Sol / Opus 5 according to benchmarks

    Perhaps with IQ2 flash will run on 128G M5?

  • nlcs 39 minutes ago
    [flagged]
  • omani 36 minutes ago
    ah, would you look at that. I was wondering why mimo 2.5 became "dumber" the last weeks. I was speculating they are probably about to release a new version of the model. because the model really acted out a lot. especially the last two weeks. dont know, was just a feeling, highly speculative.

    but now I got my "proof".

    • sandblast 26 minutes ago
      I guess that would only be possible if your provider was Xiaomi itself?
      • omani 18 minutes ago
        yes. I use opencode and opencode uses Xiaomi as a provider.
  • unpopularopp 37 minutes ago
    I've never used worst smartphones than anything from Xiaomi, bloated ad infested borderline malware territory fork of Android. Maybe just me but whenever I see them on HN I just can't think anything good about this company.
    • InsideOutSanta 18 minutes ago
      It's funny, I have the exact opposite reaction. This is probably misguided on my part, but Xiaomi is one of the very few major tech companies that I don't have an immediate strong negative reaction to. Everything I've bought from them, from robot vacuum to mobile phone, has been reasonably well designed, didn't break, and was priced fairly. I also think their car looks badass.

      I'm sure they're doing all kinds of terrible things, like all major companies. I just can't help but like them. Also, this model looks great, and I'll give their subscription a shot next month.

    • algoth1 18 minutes ago
      I still have a xiaomi mi 11 lite, my wife has a 15t. The cameras are the best for the price. The way they chove ads down your throat at every opportunity should be illegal though
    • platinumrad 34 minutes ago
      It's a big company, like Microsoft or Google. Some of their products are good and some are bad.
      • verdverm 15 minutes ago
        ironic to this thread, I have less bloatware and ads since I switched from Verzion to Pixel on Fi (many years ago)

        Curious if Verizon / ATT still force apps on your phone, eg. NFL and Amazon apps, Fi service is subpar

  • jwpapi 11 minutes ago
    In the chart they use "Pareto Line", which I think is wrong. Pareto is 20% effort leading to 80% results. Which could be interpreted as models costing 20% having 80% of peak intelligence, but that’s not what it looks like to me.

    It looks like the "Frontier Line" to me, which is also often misinterpreted. frontier does not mean the best models. It means all models that are not strictly dominated, meaning in most cases: Not same price or cheaper and more intelligent.

    I personally would like the word frontier to be used with more criterias: Open Weights, per use-case, etc etc. This would make model selection easier, but I understand it’s not an easy thing to do.

    • abound 5 minutes ago
      There are two (or more) concepts named after the same person:

      - Pareto efficiency/Pareto curves: Basically the convex hull of points along the edge of a graph, indicating the best tradeoff between the axes. This is what the post is talking about.

      - Pareto principle: this is the 80/20 rule you're talking about

    • shmolyneaux 6 minutes ago
      This is the Pareto Front [1], rather than the Pareto principle. It's the idea that anything that's more intelligent is more expensive and anything that's less expensive is less intelligent.

      [1]: https://en.wikipedia.org/wiki/Pareto_front

    • hashmush 7 minutes ago
      "Pareto" is many things, but here it does indeed refer to the frontier: https://en.wikipedia.org/wiki/Pareto_front
      • jwpapi 1 minute ago
        Thank you guys. I learned something new.