Xiaomi model product
MiMo V2 Pro
MiMo V2 Pro is Xiaomi's foundation model for coding and agent tasks, with over 1T total parameters, 42B active parameters, and support for up to 1M-token contexts.
Updated Sep 8, 2026. Default version: MiMo-V2-Pro
LLMBoard Score61.5MiMo-V2-Pro
Coverage20%7 benchmark families
Context window1MTokens
Official input price$0.435Xiaomi API
MiMo V2 Pro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiMo V2 Pro Benchmark Results
Benchmark scores for MiMo-V2-Pro.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkPinchBench | Score81.00% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkDeepSearchQA | Score86.70% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score96.80% | Rank08 | Participants36 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkClaw-Eval | Score61.50% | Rank10 | Participants14 | Percentile30.77% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score71.70% | Rank20 | Participants43 | Percentile54.76% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score78.00% | Rank23 | Participants113 | Percentile80.36% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score57.10% | Rank25 | Participants51 | Percentile52.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,433.21 rating | Rank53 | Participants97 | Percentile45.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,448.40 rating | Rank55 | Participants210 | Percentile74.16% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,436.45 rating | Rank58 | Participants210 | Percentile72.73% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,443.57 rating | Rank60 | Participants121 | Percentile50.83% | EvidenceA | Evaluated |
MiMo V2 Pro Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryexpert | Rank27 | Rating / score1,489.78 | Votes1,514 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank27 | Rating / score1,494.71 | Votes5,950 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank29 | Rating / score1,473.29 | Votes7,193 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank29 | Rating / score1,454.72 | Votes826 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank32 | Rating / score1,477.27 | Votes2,085 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank33 | Rating / score1,455.56 | Votes9,454 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank33 | Rating / score1,491.51 | Votes2,085 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank34 | Rating / score1,467.18 | Votes924 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank34 | Rating / score1,443.81 | Votes8,032 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank34 | Rating / score1,458.75 | Votes4,418 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank35 | Rating / score1,505.43 | Votes5,622 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank36 | Rating / score1,450.60 | Votes6,746 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank36 | Rating / score1,489.05 | Votes7,193 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank37 | Rating / score1,457.78 | Votes15,740 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank37 | Rating / score1,464.14 | Votes1,465 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank37 | Rating / score1,464.61 | Votes10,498 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank37 | Rating / score1,470.58 | Votes1,465 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank38 | Rating / score1,475.88 | Votes6,911 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank38 | Rating / score1,439.61 | Votes4,836 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank38 | Rating / score1,445.17 | Votes1,180 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank39 | Rating / score1,466.07 | Votes8,277 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank40 | Rating / score1,472.92 | Votes15,698 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank40 | Rating / score1,478.27 | Votes924 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank41 | Rating / score1,453.88 | Votes10,625 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank41 | Rating / score1,454.82 | Votes3,607 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank41 | Rating / score1,429.20 | Votes3,610 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank41 | Rating / score1,415.67 | Votes456 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank41 | Rating / score1,466.73 | Votes9,454 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank41 | Rating / score1,468.72 | Votes4,418 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank41 | Rating / score1,452.88 | Votes826 | ObservationsN/A | Result date |
MiMo V2 Pro Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.435 input, $0.87 output per 1M
- Official provider
- Xiaomi
- Lowest third-party
- From $1 input, $3 output per 1M via OpenCode Go
- Tracked offerings
- 8
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderXiaomi Token Plan (Singapore) | Provider model IDmimo-v2-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (China) | Provider model IDmimo-v2-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (Europe) | Provider model IDmimo-v2-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi | Provider model IDmimo-v2-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDmimo-v2-pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderZenMux | Provider model IDxiaomi/mimo-v2-pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderAbacus | Provider model IDmimo-v2-pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderNovitaAI | Provider model IDxiaomimimo/mimo-v2-pro | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
MiMo V2 Pro Runtime Performance
Provider-specific output speed and catalog latency for MiMo-V2-Pro. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiMo V2 Pro Specifications
Technical details for the model's default version.
- Version
- MiMo-V2-Pro
- Released
- Mar 18, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 1T
- Context window
- 1M
- Max output
- 16.4K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
MiMo V2 Pro Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMiMo-V2-Pro | Released | LLMBoard61.49 | Parameters1T | Context1M | Max output16.4K | Open weightsNo | LicenseProprietary |
Models similar to MiMo V2 Pro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XI
MiMo
Xiaomi
XI
MiMo V2 Flash
Xiaomi
XI
MiMo V2 Omni
Xiaomi
XI
MiMo V2.5 Pro
Xiaomi
OP
GPT-5.3-Codex
OpenAI
NV
Nemotron 3 Ultra
NVIDIA
What is MiMo V2 Pro?
Key information about MiMo V2 Pro and its available data.
MiMo V2 Pro is a Mixture-of-Experts foundation model from Xiaomi with over 1T total parameters and 42B active parameters. It uses Hybrid Attention with a 7:1 ratio and supports complex tool calling and multi-step reasoning.
Data as of 2026-09-08.
FAQ
Common questions about MiMo V2 Pro.
When was MiMo V2 Pro released?
MiMo V2 Pro's default version was released on Mar 18, 2026.
How much does MiMo V2 Pro cost?
MiMo V2 Pro's official API price is $0.435 per million input tokens and $0.87 per million output tokens via Xiaomi. The lowest tracked third-party offer starts at $1 input and $3 output via OpenCode Go.
Who created MiMo V2 Pro?
MiMo V2 Pro was created by Xiaomi.
What is the context window for MiMo V2 Pro?
The default version has a 1M token context window.
Is MiMo V2 Pro open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer MiMo V2 Pro?
8 provider offerings are linked to the default version.