Realme 5 Pro

[...] Generally, made me comfortable not scrutinizing the code line-by-line, but still needed a bit of steering once projects got to a reasonable size. [...] It also seems to be a fair bit better at design, at least for the little bit I've done, it was good at translating my concepts to practical elements on screen, and cleaned things up nicely as I made suggestions.

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.

[...] Small side note, the first gemini-2.5-pro one totally reminded me of some sad faced meme or Pepe the frog from somewhere. [...]

They promised 3.5 Pro at their next or i/o event, but the rumor is that is never going to be released because it would have been embarrassing. They just started letting their engineers use Claude, so it sounds like things may not be going so well with Gemini

[...] MiMo 2.5 Pro just reading files is an excellent security bug finder, at the pareto frontier at the time (cheapest option to find as many bugs as Opus 4.8, which was current at the time), but adding tools cratered it down to small model territory. [...]

[...] Enable models hosted in China <toggle-button If you turn this off, DeepSeek Flash & Pro both stop working: Error: Provider request failed with HTTP 403: The latest version of this model is only available hosted in China and requires explicit opt in: Kimi K3, MiMo V2.5 Pro, MiniMax M3, Qwen3.8 Max all work (remarkably!) without the box ticked! [...]

[...] On SimpleQA, a benchmark of factual recall with no tools allowed, the current leader is Gemini 2.5 Pro at 53%, so the best recall money can buy still misses half the questions. SimpleQA hasn't been updated in a long time. Gemini 2.5 Pro is a sixteen-month-old model, not "the best recall money can buy". [...]

They are doing fine as a shovel salesman (GPUs/TPUs, being the inference hardware provider, though I now wonder if their token processing stats are their own or combined with those who are running on their hardware too, I've been conditioned to be far more skeptical of Big Ai these days) On the flip side, gemini is terrible at coding by comparison, so much so google has now given all engineers access to claude. They promised us Gemini 3.5 pro at their developer event this summer, now it seems it will never be released. [...] They've removed the feedback button for "ai answers" at the top of search, that does not seem well received, it hallucinates too much (and may be a legal liability, some courts have ruled as such in the EU). [...] You can see the forced gemini usage for coding and subsequent slop in their products, especially gcloud console. I was sent the greatest slop deck by one of their sales people for Gemini Enterprise, needless to say we did not buy from them, but we did get an amazing :cursed-claude: emoji from the deck (nano banana's take on what claude looks like as a person) a rambled sample, hope this helps, I was a google superfan for a long time, I was sad to see things go south, now I'm happy that I was motivated to move off most their platforms (gmail/youtube remain)

[...] Recent experience tells me that larger models are worth it in non-obvious ways. [...]

[...] I found it after spotting it on a chart of different models and it was listed as being near Deepseek v4 Flash’s price/performance levels. I have noticed by the way that DeepSeek’s API has been pretty slow the past couple of days. [...]

[...] It's absolutely not across the board "more capable" than GPT 5 or Opus 4.1 or even Gemini 2.5 Pro. [...]

Might be missing something —- are there any issues with Gemini 3.1 Pro that aren’t there in 2.5? [...] Very competent, knows a lot, and can process tons of text (and videos, and images, and audio too iirc?). [...] None of the newer, cheaper, but obviously less intelligent benchmaxxed smaller models really seem to hold a candle to it for lots of things.

Interesting - I've been dropping into MiMo-V2.5-Pro-UltraSpeed whenever Flash seems to be "stuck" and it usually figures it out. I use UltraSpeed just because I'm so frustrated by then that I'm impatient. I still find 5.6-Sol can solve some things neither of those can, but it's so slow (and it's so hard to trace / debug the reasoning) that I just let it run overnight.

If you actually want to conduct some experiment, I'd suggest: fist iterate on the idea with o3 (best choice) or other big model (Opus 4, Gemini 2.5 Pro, Grok 3) -- ask it whether it was done before, how to improve it, what is the expected outcome, etc. [...] uv is probably the modern way to manage venv, but installing torch with CUDA support via uv is pain, what I found works is: uv pip install torch --torch-backend=cu126 (uv pip uninstall torch) lambda.ai provides high-quality environment, but it might lack cheaper GPU options. [...]

I had the chance to try out MiMo v2.5 Pro Ultraspeed (600-1000tok/s) for a couple weeks and it is amazing. Developing software becomes 95% about intent and requirements. Can’t wait for the next iteration of that.

Gosh good tiems with 2.5 pro. it was way better than anthropic. I really hope they catch up, they have a better product sense and are more reliable to their users

My coding agent VT Code has recently become a Xiaomi Orbit partner. If you want to try out Xiaomi Mimo V2.5 and V2.5 Pro in a different harness, feel free to use my VT Code. VT Code supports Mimo V2.5/Pro via official Xiaomi endpoints and via OpenRouter. Thank you! [0]

Claude thinks Humans are stupid I haven't noticed this when using Claude models in Cursor. My guess is coding task is structured, and each step has mature process, so its personality is less pronounced. I dont have experiences using Claude or Claude Code, because my email and phone numbers were banned from Anthropic following an incident where I mistakenly purchased 5 pro subscriptions fro my team for Claude Code, and later discovered that pro does not include CC, and I thus requested a refund, and then were banned shortly after. But after reading this line, I certainly can connect back to the general impression. That is, among all the cursor models, the output of Claude certainly matches this sentiment of "Claude thinks Humans are stupid" Looking from a regulation perspective: 1. Frontier labs certainly produces models that reflect their own hidden biases. That's analogous to commonly identified among human organizations in their dealing of other humans (hiring, product design etc.) 2. They themselves are not willing to admit or do anything about this. 3. It's therefore effective for regulation to cover this and design objective measurements to assess such things.

Which is why I actually used all those models. At work I am stuck with Claude because it is what the employer provides. In my home setup I use a combination of different models; mostly GLM-5.3, DS-V4-Flash, and MiMo-2.5-pro. I vastly prefer my home setup.