Xiaomi model product
MiMo V2.5 Pro
02T-parameter sparse Mixture-of-Experts language model with 42B active parameters and a 1M-token context window.
Updated Oct 23, 2026. Default version: MiMo-V2.5-Pro
LLMBoard Score45.3MiMo-V2.5-Pro
Coverage100%28 benchmark families
Context window1MTokens
Official input price$0.435Xiaomi API
MiMo V2.5 Pro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiMo V2.5 Pro Benchmark Results
Benchmark scores for MiMo-V2.5-Pro.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkARC-C | Score97.20% | Rank01 | Participants35 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCMMLU | Score90.20% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE (Impl.) | Score3.40 rank | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score99.60% | Rank01 | Participants48 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMBPP+ | Score74.10% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMiMo Coding Bench | Score73.70% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTAU3-Bench | Score72.90% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAIME | Score37.30% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBBH | Score88.40% | Rank02 | Participants13 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Verified (Agentless) | Score35.70% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkGraphWalks | Score62.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTriviaQA | Score81.30% | Rank03 | Participants18 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score85.60% | Rank03 | Participants23 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkDROP | Score86.30% | Rank04 | Participants30 | Percentile89.66% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU | Score83.60% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score89.80% | Rank05 | Participants28 | Percentile85.19% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score79.86% | Rank05 | Participants168 | Percentile97.60% | EvidenceB | EvaluatedN/A |
| BenchmarkC-Eval | Score91.50% | Rank06 | Participants20 | Percentile73.68% | EvidenceC | Evaluated |
| BenchmarkClaw-Eval | Score64.00% | Rank06 | Participants14 | Percentile61.54% | EvidenceC | Evaluated |
| BenchmarkWildClawBench | Score43.00% | Rank06 | Participants6 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHumanEval+ | Score75.60% | Rank07 | Participants10 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMATH | Score86.20% | Rank11 | Participants71 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score68.40% | Rank13 | Participants53 | Percentile76.92% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score92.80% | Rank15 | Participants50 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score89.40% | Rank16 | Participants103 | Percentile85.29% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score41.50% | Rank18 | Participants29 | Percentile39.29% | EvidenceB | Evaluated |
| BenchmarkSWE-Bench Verified | Score78.90% | Rank20 | Participants120 | Percentile84.03% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability No Prereq | Score0.96% | Rank27 | Participants45 | Percentile40.91% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score79.67% | Rank28 | Participants193 | Percentile85.94% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Bash Reliability | Score-0.13% | Rank28 | Participants44 | Percentile37.21% | EvidenceA | Evaluated |
MiMo V2.5 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 | Categoryfrench | Rank14 | Rating / score1,502.55 | Votes2,293 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank14 | Rating / score1,436.24 | Votes679 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank14 | Rating / score1,453.01 | Votes783 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank15 | Rating / score1,493.94 | Votes21,733 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank16 | Rating / score1,509.44 | Votes21,070 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank17 | Rating / score1,480.76 | Votes3,467 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank17 | Rating / score1,500.71 | Votes4,386 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank18 | Rating / score1,501.07 | Votes20,773 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank18 | Rating / score1,480.46 | Votes32,214 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank19 | Rating / score1,494.64 | Votes30,284 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank19 | Rating / score1,527.91 | Votes20,046 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank19 | Rating / score1,477.68 | Votes3,117 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank20 | Rating / score1,466.03 | Votes14,831 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank21 | Rating / score1,485.50 | Votes50,452 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank21 | Rating / score1,510.41 | Votes6,428 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank21 | Rating / score1,415.30 | Votes780 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank21 | Rating / score1,464.54 | Votes1,896 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank22 | Rating / score1,500.55 | Votes7,606 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank22 | Rating / score1,475.40 | Votes25,875 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank22 | Rating / score1,481.21 | Votes34,292 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank22 | Rating / score1,508.94 | Votes29,971 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank23 | Rating / score1,476.73 | Votes32,276 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank23 | Rating / score1,463.68 | Votes1,376 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank23 | Rating / score1,481.38 | Votes11,313 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank24 | Rating / score1,486.77 | Votes2,864 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank24 | Rating / score1,491.09 | Votes4,199 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank24 | Rating / score1,475.68 | Votes13,010 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank24 | Rating / score1,468.99 | Votes2,383 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank24 | Rating / score1,473.58 | Votes13,328 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank24 | Rating / score1,473.79 | Votes25,265 | ObservationsN/A | Result date |
MiMo V2.5 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 $0.3045 input, $0.609 output per 1M via OpenRouter
- Tracked offerings
- 23
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderXiaomi Token Plan (Singapore) | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (China) | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (Europe) | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderOpenRouter | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.3045 | Output / 1M$0.609 | Context1.1M | Updated |
| ProviderVercel AI Gateway | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.3045 | Output / 1M$0.609 | Context1.1M | Updated |
| ProviderNanoGPT | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderLLMTR | Provider model IDmimo/mimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderXiaomi | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderRequesty | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1.1M | Updated |
| ProviderPioneer | Provider model IDXiaomiMiMo/MiMo-V2.5-Pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1.1M | Updated |
| ProviderStandard Compute | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.435 | Output / 1M$0.87 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$0.4602 | Output / 1M$0.9205 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.48 | Output / 1M$0.96 | Context1M | Updated |
| ProviderKenari | Provider model IDmimo-v2-5-pro | Regionglobal | Input / 1M$0.52 | Output / 1M$1.03 | Context1M | Updated |
| ProviderNovita AI | Provider model IDxiaomimimo/mimo-v2.5-pro | Regionglobal | Input / 1M$0.522 | Output / 1M$1.04 | Context1M | Updated |
| ProviderDigitalOcean | Provider model IDmimo-v2.5-pro | Regionglobal | Input / 1M$0.80 | Output / 1M$3 | Context262.1K | Updated |
| ProviderDeep Infra | Provider model IDXiaomiMiMo/MiMo-V2.5-Pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderHugging Face | Provider model IDXiaomiMiMo/MiMo-V2.5-Pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderZenMux | Provider model IDxiaomi/mimo-v2.5-pro | Regionglobal | Input / 1M$1 | Output / 1M$3 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/mimo-v2.5-pro | Regionglobal | Input / 1M$1.74 | Output / 1M$3.48 | Context1M | Updated |
MiMo V2.5 Pro Runtime Performance
Provider-specific output speed and catalog latency for MiMo-V2.5-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 V2.5 Pro Specifications
Technical details for the model's default version.
- Version
- MiMo-V2.5-Pro
- Released
- Apr 27, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 1T
- Context window
- 1M
- Max output
- 1M
- Inputs
- audio, text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiMo V2.5 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-V2.5-Pro | Released | LLMBoard45.32 | Parameters1T | Context1M | Max output1M | Open weightsYes | LicenseMIT |
Models similar to MiMo V2.5 Pro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XI
MiMo V2 Omni
Xiaomi
XI
MiMo V2 Flash
Xiaomi
XI
MiMo
Xiaomi
XI
MiMo V2 Pro
Xiaomi
XI
MiMo V2.6 Flash
Xiaomi
XI
MiMo V2.6 Pro
Xiaomi
What is MiMo V2.5 Pro?
Key information about MiMo V2.5 Pro and its available data.
5 Pro is a Xiaomi language model that inherits the MiMo-V2-Flash hybrid-attention and Multi-Token Prediction design. It uses supervised fine-tuning, domain-specialized reinforcement learning, and Multi-Teacher On-Policy Distillation for software engineering, long-horizon agentic tasks, and ultra-long-context coherence.
Data as of 2026-10-22.
FAQ
Common questions about MiMo V2.5 Pro.
When was MiMo V2.5 Pro released?
MiMo V2.5 Pro's default version was released on Apr 27, 2026.
How much does MiMo V2.5 Pro cost?
MiMo V2.5 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 $0.3045 input and $0.609 output via OpenRouter.
Who created MiMo V2.5 Pro?
MiMo V2.5 Pro was created by Xiaomi.
What is the context window for MiMo V2.5 Pro?
The default version has a 1M token context window.
Is MiMo V2.5 Pro open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiMo V2.5 Pro?
23 provider offerings are linked to the default version.