Xiaomi model product
MiMo
5 is Xiaomi's omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window.
Updated Sep 8, 2026. Default version: MiMo-V2.5
LLMBoard Score60.0MiMo-V2.5
Coverage0%9 benchmark families
Context window1MTokens
Official input price$0.14Xiaomi API
MiMo Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiMo Benchmark Results
Benchmark scores for MiMo-V2.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkDailyOmni | Score83.50% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHR-Bench (4k) | Score88.50% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkResearchClawBench | Score16.91% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGraphWalks | Score87.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMiMo Coding Bench | Score71.80% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench | Score87.20% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkVideoHolmes | Score64.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkVideo-MME | Score87.70% | Rank04 | Participants17 | Percentile81.25% | EvidenceC | Evaluated |
| BenchmarkClaw-Eval | Score63.20% | Rank07 | Participants14 | Percentile53.85% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score65.80% | Rank16 | Participants51 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score36.73% | Rank21 | Participants26 | Percentile20.00% | EvidenceB | Evaluated |
| BenchmarkMMMU-Pro | Score77.90% | Rank22 | Participants69 | Percentile69.12% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score81.00% | Rank25 | Participants55 | Percentile55.56% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score56.10% | Rank34 | Participants55 | Percentile38.89% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,248.06 rating | Rank43 | Participants107 | Percentile60.38% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,234.85 rating | Rank45 | Participants107 | Percentile58.49% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,437.71 rating | Rank49 | Participants97 | Percentile50.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,438.80 rating | Rank64 | Participants121 | Percentile47.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,427.52 rating | Rank69 | Participants210 | Percentile67.46% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,433.81 rating | Rank72 | Participants210 | Percentile66.03% | EvidenceA | Evaluated |
MiMo Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorychinese | Rank19 | Rating / score1,315.45 | Votes1,102 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank22 | Rating / score1,326.39 | Votes1,102 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank31 | Rating / score1,194.33 | Votes143 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank33 | Rating / score1,473.68 | Votes1,421 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank33 | Rating / score1,452.36 | Votes2,032 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank33 | Rating / score1,339.16 | Votes375 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank33 | Rating / score1,380.76 | Votes505 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank34 | Rating / score1,169.32 | Votes143 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank35 | Rating / score1,271.34 | Votes6,149 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank37 | Rating / score1,503.96 | Votes12,204 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank37 | Rating / score1,262.61 | Votes9,374 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank37 | Rating / score1,267.96 | Votes6,149 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank38 | Rating / score1,258.24 | Votes16,547 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank39 | Rating / score1,461.46 | Votes14,210 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank39 | Rating / score1,445.16 | Votes2,003 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank39 | Rating / score1,243.81 | Votes9,374 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank41 | Rating / score1,479.58 | Votes3,656 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank41 | Rating / score1,487.49 | Votes17,857 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank42 | Rating / score1,266.01 | Votes3,252 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank42 | Rating / score1,249.48 | Votes16,547 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank43 | Rating / score1,484.94 | Votes1,799 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank43 | Rating / score1,481.66 | Votes13,619 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank43 | Rating / score1,248.06 | Votes23,076 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank44 | Rating / score1,469.17 | Votes12,853 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank44 | Rating / score1,462.43 | Votes4,401 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank44 | Rating / score1,434.19 | Votes14,982 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank44 | Rating / score1,258.71 | Votes3,252 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank44 | Rating / score1,213.63 | Votes847 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank45 | Rating / score1,463.25 | Votes18,162 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank45 | Rating / score1,226.48 | Votes847 | ObservationsN/A | Result date |
MiMo Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.14 input, $0.28 output per 1M
- Official provider
- Xiaomi
- Lowest third-party
- From $0.14 input, $0.28 output per 1M via NanoGPT
- Tracked offerings
- 26
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderXiaomi Token Plan (Singapore) | Provider model IDmimo-v2.5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderKenari | Provider model IDmimo-v2-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (China) | Provider model IDmimo-v2.5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderInferX | Provider model IDmimo-v25 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (Europe) | Provider model IDmimo-v2.5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNaN | Provider model IDmimo-v2.5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNanoGPT | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderImpossibl | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1.1M | Updated |
| ProviderOpenCode Go | Provider model IDmimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderLLMTR | Provider model IDmimo/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderXiaomi | Provider model IDmimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderRequesty | Provider model IDmimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1.1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDmimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderPioneer | Provider model IDXiaomiMiMo/MiMo-V2.5 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1.1M | Updated |
| ProviderCrossModel | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.16 | Output / 1M$0.32 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDXiaomiMiMo/MiMo-V2.5 | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDXiaomiMiMo/MiMo-V2.5 | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context262.1K | Updated |
| ProviderAmbient | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context1M | Updated |
| ProviderZenMux | Provider model IDxiaomi/mimo-v2.5 | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context1M | Updated |
| ProviderVenice AI | Provider model IDxiaomi-mimo-v2-5 | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDmimo-v2-5 | Regionglobal | Input / 1M$0.70 | Output / 1M$1.4 | Context1M | Updated |
MiMo Runtime Performance
Provider-specific output speed and catalog latency for MiMo-V2.5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed5.39 tok/s | Catalog Latency7.82 s | Max Input262.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiMo Specifications
Technical details for the model's default version.
- Version
- MiMo-V2.5
- Released
- Apr 22, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 310.8B
- Context window
- 1M
- Max output
- 131.1K
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiMo 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 | Released | LLMBoard60.00 | Parameters310.8B | Context1M | Max output131.1K | Open weightsYes | LicenseMIT |
Models similar to MiMo
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XI
MiMo V2 Pro
Xiaomi
XI
MiMo V2 Flash
Xiaomi
XI
MiMo V2 Omni
Xiaomi
XI
MiMo V2.5 Pro
Xiaomi
MA
Kimi K2 Thinking
Moonshot AI
BA
ERNIE 5.0
Baidu
What is MiMo?
Key information about MiMo and its available data.
5 is an omnimodal sparse Mixture-of-Experts model built on the MiMo-V2-Flash backbone, with dedicated vision and audio encoders for text, image, video, and audio understanding.
It is post-trained with SFT, agentic reinforcement learning, and Multi-Teacher On-Policy Distillation for multimodal perception, long-context reasoning, and agentic workflows.
Data as of 2026-09-08.
FAQ
Common questions about MiMo.
When was MiMo released?
MiMo's default version was released on Apr 22, 2026.
How much does MiMo cost?
MiMo's official API price is $0.14 per million input tokens and $0.28 per million output tokens via Xiaomi. The lowest tracked third-party offer starts at $0.14 input and $0.28 output via NanoGPT.
Who created MiMo?
MiMo was created by Xiaomi.
What is the context window for MiMo?
The default version has a 1M token context window.
Is MiMo open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiMo?
26 provider offerings are linked to the default version.