Xiaomi model product
MiMo V2.6 Flash
6 Flash is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 309B total parameters and 15B active parameters.
Updated Nov 11, 2026. Default version: MiMo-V2.6-Flash
LLMBoard Score73.0MiMo-V2.6-Flash
Coverage20%14 benchmark families
Context window1MTokens
Official input price$0.14Xiaomi API
MiMo V2.6 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiMo V2.6 Flash Benchmark Results
Benchmark scores for MiMo-V2.6-Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCyberGym | Score95.10% | Rank01 | Participants23 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMiMo Cyber Bench | Score77.20% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMiMo Visual Coding | Score71.50% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAutomationBench v1.0.6 | Score52.30% | Rank03 | Participants7 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkMiMo Coding Bench | Score61.20% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkToolathlon-Verified | Score73.60% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkJobBench | Score61.20% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSEC-bench Pro | Score47.50% | Rank08 | Participants8 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkExploitBench | Score25.30% | Rank09 | Participants9 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score80.80% | Rank09 | Participants28 | Percentile70.37% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score4.99% | Rank09 | Participants43 | Percentile80.95% | EvidenceA | Evaluated |
| BenchmarkExploitGym | Score6.00% | Rank11 | Participants11 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score87.60% | Rank11 | Participants56 | Percentile81.82% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score2.31% | Rank12 | Participants43 | Percentile73.81% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,636.52 rating | Rank12 | Participants109 | Percentile89.81% | EvidenceA | Evaluated |
| BenchmarkProgram Bench | Score26.00% | Rank16 | Participants20 | Percentile21.05% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score-0.69% | Rank17 | Participants43 | Percentile61.90% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score0.09% | Rank19 | Participants43 | Percentile57.14% | EvidenceA | Evaluated |
| BenchmarkAgents' Last Exam | Score27.60% | Rank20 | Participants26 | Percentile24.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score67.90% | Rank26 | Participants54 | Percentile52.83% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score28.80% | Rank26 | Participants35 | Percentile26.47% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score-4.38% | Rank28 | Participants43 | Percentile35.71% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score-1.06% | Rank30 | Participants44 | Percentile32.56% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score-4.00% | Rank40 | Participants43 | Percentile7.14% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,450.32 rating | Rank41 | Participants221 | Percentile81.82% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,259.56 rating | Rank43 | Participants113 | Percentile62.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,247.91 rating | Rank43 | Participants113 | Percentile62.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,449.42 rating | Rank51 | Participants134 | Percentile62.41% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,447.84 rating | Rank62 | Participants221 | Percentile72.27% | EvidenceA | Evaluated |
MiMo V2.6 Flash Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent task outcome explicit | Categoryoverall | Rank09 | Rating / score0.05 | VotesN/A | Observations14.2K | Result date |
| Arenaagent steerability | Categoryoverall | Rank12 | Rating / score0.02 | VotesN/A | Observations132.7K | Result date |
| Arenawebdev | Categoryoverall | Rank12 | Rating / score1,636.52 | Votes8,576 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank12 | Rating / score1,636.52 | Votes8,576 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank12 | Rating / score1,636.38 | Votes1,359 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank13 | Rating / score1,593.31 | Votes3,254 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank14 | Rating / score1,652.50 | Votes5,368 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank16 | Rating / score1,335.00 | Votes320 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank17 | Rating / score-0.01 | VotesN/A | Observations7.2K | Result date |
| Arenaagent | Categoryoverall | Rank19 | Rating / score0.00 | VotesN/A | Observations3.8M | Result date |
| Arenatext | Categoryhard prompts english | Rank21 | Rating / score1,488.36 | Votes4,999 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank22 | Rating / score1,497.66 | Votes5,178 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank22 | Rating / score1,346.20 | Votes320 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank23 | Rating / score1,493.14 | Votes8,161 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank24 | Rating / score1,507.10 | Votes1,820 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank25 | Rating / score1,498.47 | Votes2,085 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank26 | Rating / score1,484.35 | Votes1,216 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank26 | Rating / score1,501.63 | Votes4,908 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank28 | Rating / score1,473.04 | Votes7,898 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank28 | Rating / score1,477.33 | Votes856 | ObservationsN/A | Result date |
| Arenaagent bash reliability | Categoryoverall | Rank28 | Rating / score-0.04 | VotesN/A | Observations401.1K | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank30 | Rating / score-0.01 | VotesN/A | Observations63.7K | Result date |
| Arenatext factuality | Categorycoding | Rank32 | Rating / score1,519.46 | Votes5,099 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank33 | Rating / score1,512.29 | Votes1,761 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank33 | Rating / score1,450.70 | Votes3,857 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank33 | Rating / score1,501.07 | Votes8,145 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank33 | Rating / score1,273.82 | Votes2,095 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank34 | Rating / score1,509.24 | Votes1,485 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank35 | Rating / score1,472.34 | Votes7,881 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank36 | Rating / score1,457.85 | Votes357 | ObservationsN/A | Result date |
MiMo V2.6 Flash 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 $0.10 input, $0.28 output per 1M via Kilo Gateway
- Tracked offerings
- 27
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderXiaomi Token Plan (China) | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (Europe) | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXiaomi Token Plan (Singapore) | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNaN | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAMD | Provider model IDMiMo-V2.6-Flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.10 | Output / 1M$0.28 | Context1M | Updated |
| ProviderVultr | Provider model IDmimo-v2.6-flash-rl | Regionglobal | Input / 1M$0.10 | Output / 1M$0.25 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderXiaomi | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDmimo-v2-6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1.1M | Updated |
| ProviderOpenCode Go | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDXiaomiMiMo/MiMo-V2.6-Flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderRequesty | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderTempr Gateway | Provider model IDxiaomi-mimo/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderNovita AI | Provider model IDxiaomimimo/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderBoundless | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderStandard Compute | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderOllama Cloud | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.155 | Output / 1M$0.31 | Context1M | Updated |
| ProviderCrossModel | Provider model IDxiaomi/mimo-v2.6-flash | Regionglobal | Input / 1M$0.16 | Output / 1M$0.32 | Context1M | Updated |
| Providerabove.dev | Provider model IDmimo-v2.6-flash | Regionglobal | Input / 1M$0.1692 | Output / 1M$0.3385 | Context1M | Updated |
| ProviderVenice AI | Provider model IDxiaomi-mimo-v2-6-flash | Regionglobal | Input / 1M$0.175 | Output / 1M$0.35 | Context1M | Updated |
MiMo V2.6 Flash Runtime Performance
Provider-specific output speed and catalog latency for MiMo-V2.6-Flash. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderXiaomi | Output Speed6.45 tok/s | Catalog Latency8.63 s | Max Input1M | Max OutputN/A | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiMo V2.6 Flash Specifications
Technical details for the model's default version.
- Version
- MiMo-V2.6-Flash
- Released
- Sep 22, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 309B
- Context window
- 1M
- Max output
- N/A
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiMo V2.6 Flash 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-V2.6-Flash | Released | LLMBoard72.97 | Parameters309B | Context1M | Max outputN/A | Open weightsYes | LicenseMIT |
Models similar to MiMo V2.6 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XI
MiMo V2.6 Pro
Xiaomi
XI
MiMo V2 Pro
Xiaomi
XI
MiMo
Xiaomi
XI
MiMo V2 Flash
Xiaomi
XI
MiMo V2 Omni
Xiaomi
XI
MiMo V2.5 Pro
Xiaomi
What is MiMo V2.6 Flash?
Key information about MiMo V2.6 Flash and its available data.
6 Flash is a Xiaomi large language model that understands text, images, video, and audio and produces text output. It has a 1,048,576-token context window.
Data as of 2026-11-10.
FAQ
Common questions about MiMo V2.6 Flash.
When was MiMo V2.6 Flash released?
MiMo V2.6 Flash's default version was released on Sep 22, 2026.
How much does MiMo V2.6 Flash cost?
MiMo V2.6 Flash'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 $0.10 input and $0.28 output via Kilo Gateway.
Who created MiMo V2.6 Flash?
MiMo V2.6 Flash was created by Xiaomi.
What is the context window for MiMo V2.6 Flash?
The default version has a 1M token context window.
Is MiMo V2.6 Flash open weight?
Yes. The default version is marked as open weight under MIT.