MiMo-V2.5-Pro
Xiaomihuggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
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....
Updated 4 h ago · first seen 11 Sept 2026
model_01M294WW0THY1JB2Y40QX7ZJ4S
Overview
Identity
- Canonical model
- Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- 1
- API aliases
- mimo-v2-5-promimo-v2-5-pro-non-reasoningxiaomi/mimo-v2.5-proIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 1Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under MIT; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
Yes
Redistribution
Yes
Derivatives
Yes
Licence: MIT License (permissive · SPDX MIT)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Capabilities
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Languages
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
Benchmarks30
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 30 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →
Providers & Pricing1
All offers in the price terminal →USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →
Price history
Output price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $0.8711 Sept 2026
Input price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouterfirst observed $0.43511 Sept 2026
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
- A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
- Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
- Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Versions & Artifacts0
Version history
Context window2 changes
11 Sept 2026→11 Sept 2026→12 Sept 2026current
Licensefirst observation only
12 Sept 2026current
Max outputfirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
12 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Timeline18
Full timeline →MiMo-V2.5-Pro: release date changed from 2026-04-22 to 2026-04-27
Release date22 Apr 2026→27 Apr 2026huggingfaceMiMo-V2.5-Pro scores 43.18% on Terminal-Bench
artificial_analysisMiMo-V2.5-Pro scores 65.17% on Terminal-Bench
artificial_analysisMiMo-V2.5-Pro scores 0% on Terminal-Bench
artificial_analysisMiMo-V2.5-Pro scores 35.68% on Humanity's Last Exam
artificial_analysisMiMo-V2.5-Pro scores 86.57% on GPQA Diamond
artificial_analysisMiMo-V2.5-Pro scores 26.41 on Artificial Analysis Intelligence Index
artificial_analysisMiMo-V2.5-Pro scores 35.61% on Terminal-Bench
artificial_analysisMiMo-V2.5-Pro scores 14.78% on Humanity's Last Exam
artificial_analysisMiMo-V2.5-Pro scores 76.16% on GPQA Diamond
artificial_analysisMiMo-V2.5-Pro scores 18.29 on Artificial Analysis Intelligence Index
artificial_analysisMiMo-V2.5-Pro: reasoning changed from false to true
ReasoningNo→Yesartificial_analysisMiMo-V2.5-Pro: context length changed from 1000000 to 1050000
Context window1M tokens→1.05M tokensopenrouter
Change history69
Viewing AI Atlas as of 15 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 15 Sept 2026 44 claims in force
- Release date
- 27 Apr 2026
- Openness
- open-weights
- License
- MIT
- Architecture
- MiMoV2ForCausalLM
- Parameters
- 1.02T
- Context window
- 1.05M tokens
- Max output
- 131.1K tokens
- Modalities
- text
- Input modalities
- text
- Output modalities
- text
- Languages
- en, zh
- Quantization format
- fp8
- File size
- 1033.4 GB
- Hugging Face repo
- XiaomiMiMo/MiMo-V2.5-Pro
- Pipeline tag
- text-generation
- Model card
- Downloads
- 24,775
- Likes
- 749
- Aa context window
- 1,000,000
- Aa openness
- open-weights
- Access
- open
- Artifact kind
- quantization
- Commercial use allowed
- Yes
- Derivatives allowed
- Yes
- Hf inference providers
- deepinfra, novita
- Is quantized
- Yes
- Last modified
- 2026-07-09T04:20:08+00:00
- Library name
- transformers
- License key
- MIT
- License raw
- mit
- Aa median output tokens per second
- 39.1
- Downloads all time
- 327,078
- Model type
- mimo_v2
- Openrouter id
- xiaomi/mimo-v2.5-pro
- Openrouter listed at
- 22 Apr 2026
- Reasoning
- Yes
- Redistribution allowed
- Yes
- Structured output
- Yes
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Tags
- agent, code, custom_code, en, fp8, long-context, mimo_v2, safetensors, text-generation, transformers, zh
- Tool calling
- Yes
- Weights available
- Yes
- Weights dtype
- BF16, F32, F8_E4M3
Release daterelease_date2
Opennessopenness2
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length4
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Languageslanguages1
Quantization formatquant_format1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads5
Likesmetric.likes3
Aa context windowaa_context_window1
Aa opennessaa_openness1
Accessaccess1
Artifact kindartifact_kind1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Hf inference providershf_inference_providers1
Is quantizedis_quantized1
Last modifiedlast_modified1
Library namelibrary_name1
License keylicense_key1
License rawlicense_raw1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second9
Downloads all timemetric.downloads_all_time5
Model typemodel_type1
Openrouter idopenrouter_id1
Openrouter listed atopenrouter_listed_at1
Reasoningreasoning3
Redistribution allowedredistribution_allowed1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Weights availableweights_available1
Weights dtypeweights_dtype1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
44
Source tiers
T244
Freshest observation
4 h ago
Conflicts
None
Source documents 4
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →