MiMo V2.5 Pro
8096°
Run this model
Offers / Ads
Xiaomi | 1,050,000 token context | $0.43/M input, $0.87/M output. MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
MiMo-V2.5-Pro is Xiaomi's flagship open-weights MoE model, with 1.02T total parameters and 42B active, built specifically for agentic work: multi-step software engineering, long-horizon tasks, and trajectories spanning thousands of tool calls. A 1M-token context window and Multi-Token Prediction architecture that triples output speed make it a practical choice for agent framework integration. If your workload is complex, autonomous and long-running, this is what Xiaomi built it for.
Known for
- Sustains coherent trajectories across thousands of tool calls autonomously
- 1M-token context window suited to large codebases and long-horizon agents
- MoE design: 1.02T total params, only 42B active at inference
- Multi-Token Prediction triples output speed during inference
- Top results on SWE-bench Pro and agentic benchmarks ClawEval and GDPVal
Watch out for
- 1.02T total parameters means local deployment requires serious multi-GPU infrastructure despite the 42B active figure.
- Open weights are released in FP8 mixed precision; check your inference stack supports that format before downloading.
- Licence terms are not detailed in the model card; verify permitted uses on the Hugging Face repository before commercial deployment.
Prompts to try
Autonomous repo bug hunt
You have access to a shell and file system tools. Clone the repository at the URL I provide, reproduce the failing test in the issue tracker, trace the root cause across files, write a fix, and open a summary of every tool call you made and why. Start with: https://github.com/pallets/flask/issues/5508
Multi-step refactor plan
I have a Python monolith of roughly 8,000 lines that mixes database access, business logic and HTTP handlers in the same files. Produce a phased refactor plan: identify the dependency graph, propose a module structure, list the order of changes to avoid breaking tests at each step, and flag the three riskiest moves.
Long document cross-reference
I am pasting a 200-page technical specification below. Read the entire document, then: list every requirement that contradicts another requirement, cite both by section number, and suggest the minimal wording change that resolves each conflict. Specification: [paste here]
Compare with
- MiMo-V2.6-Pro-UltraSpeedAPI-only model1,048,576 token context · $4.35/M input, $8.70/M output
- MiMo-V2.6-FlashOpen-weights model1,050,000 token context · $0.14/M input, $0.28/M output
- MiMo-V2.5Open-weights model1,050,000 token context · $0.14/M input, $0.28/M output
- MiMo-V2.6-ProOpen-weights model1,050,000 token context · $0.43/M input, $0.87/M output
More text models from xiaomi
Questions people ask
- Are the weights open and can I run MiMo-V2.5-Pro locally?
- Yes, the weights are publicly available on Hugging Face under XiaomiMiMo/MiMo-V2.5-Pro. Running it locally is technically possible but demanding: the model has 1.02T total parameters in FP8 mixed precision, so you will need substantial multi-GPU hardware.
- What does MiMo-V2.5-Pro cost and what is the context length?
- Via Xiaomi's API it is priced at $0.43 per million input tokens and $0.87 per million output tokens, with a context window of up to 1,000,000 tokens.
- How does MiMo-V2.5-Pro differ from MiMo-V2.5 (the smaller model)?
- MiMo-V2.5-Pro scales to 1.02T total parameters versus 310B, extends context from the smaller model's window to 1M tokens, and is post-trained with large-scale agentic reinforcement learning specifically for complex software engineering and long-horizon autonomous tasks.
Captain's verdictA serious agentic workhorse from Xiaomi: the 1M context and MTP speed gains are real advantages, if you have the hardware or the API budget.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #73 Hottest Text / LLM model · #73 Hottest Text / LLM text model
Not this creator?
Get your own badge
MiMo V2.5 Pro Popularity Trend
Heat score since 22 Apr 2026
Heat score
8,096°
This week
▲
3.4%
8,091° then, 8,096° now
This month
▲
16.6%
8,073° then, 8,096° now
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,096°
OpenRouter tokens
45,007,664,648 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 4,500 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,096°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.4,500 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,096°8,096°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,096°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
MiMo V2.5 Pro is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153