Xiaomi model product
MiMo V2 Omni is Xiaomi's multimodal foundation model for understanding image, video, and audio inputs.
Updated Oct 23, 2026. Default version: MiMo-V2-Omni
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for MiMo-V2-Omni.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMM-BrowserComp | Score52.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOmniGAIA | Score49.80% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkPinchBench | Score81.20% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkClaw-Eval | Score54.80% | Rank13 | Participants14 | Percentile7.69% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score74.80% | Rank42 | Participants120 | Percentile65.55% | EvidenceC | Evaluated |
| BenchmarkAA LCR v1.1 | Score75.00% | Rank62 | Participants193 | Percentile68.23% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision Style Control | Score1,215.89 rating | Rank64 | Participants113 | Percentile43.75% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,227.65 rating | Rank65 | Participants113 | Percentile42.86% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,435.32 rating | Rank78 | Participants131 | Percentile40.77% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score22.10% | Rank82 | Participants200 | Percentile59.30% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,423.02 rating | Rank83 | Participants218 | Percentile62.21% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score53.54% | Rank84 | Participants168 | Percentile50.30% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,430.66 rating | Rank86 | Participants218 | Percentile60.83% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score82.83% | Rank87 | Participants199 | Percentile56.57% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score1.14% | Rank92 | Participants200 | Percentile54.27% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score19.30% | Rank129 | Participants201 | Percentile36.00% | EvidenceB | EvaluatedN/A |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryindustry mathematical | Rank44 | Rating / score1,451.98 | Votes935 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank48 | Rating / score1,271.23 | Votes693 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank49 | Rating / score1,283.84 | Votes693 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank52 | Rating / score1,500.86 | Votes5,879 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank53 | Rating / score1,256.16 | Votes2,813 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank55 | Rating / score1,455.50 | Votes6,707 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank55 | Rating / score1,480.72 | Votes6,693 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank55 | Rating / score1,438.52 | Votes884 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank57 | Rating / score1,428.64 | Votes7,039 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank57 | Rating / score1,441.37 | Votes9,194 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank58 | Rating / score1,466.11 | Votes5,891 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank58 | Rating / score1,444.72 | Votes3,506 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank58 | Rating / score1,255.10 | Votes2,813 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank59 | Rating / score1,456.96 | Votes9,179 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank59 | Rating / score1,253.15 | Votes1,629 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank60 | Rating / score1,464.33 | Votes1,209 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank60 | Rating / score1,241.97 | Votes4,294 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank61 | Rating / score1,472.02 | Votes1,817 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank61 | Rating / score1,481.57 | Votes8,352 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank61 | Rating / score1,226.40 | Votes4,294 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank62 | Rating / score1,449.55 | Votes1,046 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank62 | Rating / score1,450.74 | Votes1,433 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank62 | Rating / score1,454.50 | Votes1,046 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank62 | Rating / score1,230.41 | Votes7,549 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank63 | Rating / score1,246.87 | Votes1,629 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank64 | Rating / score1,429.67 | Votes4,179 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank64 | Rating / score1,451.48 | Votes3,506 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank64 | Rating / score1,238.15 | Votes7,549 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank64 | Rating / score1,215.89 | Votes10,650 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank65 | Rating / score1,448.66 | Votes2,141 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderXiaomi | Provider model IDmimo-v2-omni | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context262.1K | Updated |
| ProviderZenMux | Provider model IDxiaomi/mimo-v2-omni | Regionglobal | Input / 1M$0.40 | Output / 1M$2 | Context265K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for MiMo-V2-Omni. Runtime does not affect the capability score.
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.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMiMo-V2-Omni | Released | LLMBoard48.88 | ParametersN/A | Context262K | Max output16.4K | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about MiMo V2 Omni and its available data.
MiMo V2 Omni is an omni foundation model from Xiaomi that combines dedicated image, video, and audio encoders in a shared backbone. It supports structured tool calling, function execution, UI grounding, over 10 hours of continuous audio understanding, and a 256K token context window.
Data as of 2026-10-22.
Common questions about MiMo V2 Omni.
MiMo V2 Omni's default version was released on Mar 18, 2026.
MiMo V2 Omni'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 $0.40 input and $2 output via ZenMux.
MiMo V2 Omni was created by Xiaomi.
The default version has a 262K token context window.
No. The default version is not marked as having publicly available weights.
2 provider offerings are linked to the default version.