Xiaomi model product
MiMo V2 Flash
MiMo-V2-Flash is a powerful, efficient, and ultra-fast foundation language model that excels in reasoning, coding, and agentic scenarios.
Updated Aug 12, 2026. Default version: MiMo-V2-Flash
LLMBoard score51.3MiMo-V2-Flash
Coverage80%15 benchmark families
Context window262.1KTokens
Official input price$0.14Xiaomi API
MiMo V2 Flash Specifications
Technical details for the model's default version.
- Version
- MiMo-V2-Flash
- Released
- Dec 16, 2025
- Knowledge cutoff
- Dec 1, 2024
- Parameters
- 309B
- Context window
- 262.1K
- Max output
- 65.5K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiMo V2 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiMo V2 Flash Benchmark Results
Benchmark scores for MiMo-V2-Flash.
| Arena-Hard v2 | 86.2% | 01 | 16 | 100.0% | C | |
| Tau-bench | 80.3% | 03 | 6 | 60.0% | C | |
| MRCR | 45.7% | 06 | 7 | 16.7% | C | |
| LongBench v2 | 60.6% | 09 | 17 | 50.0% | C | |
| SWE-bench Multilingual | 71.7% | 15 | 34 | 57.6% | C | |
| LiveCodeBench v6 | 80.6% | 19 | 53 | 65.4% | C | |
| Terminal-Bench | 30.5% | 19 | 25 | 25.0% | C | |
| HMMT 2025 | 84.4% | 22 | 33 | 34.4% | C | |
| MMLU-Pro | 84.9% | 22 | 129 | 83.6% | C | |
| AIME 2025 | 94.1% | 24 | 114 | 79.7% | C | |
| BrowseComp | 58.3% | 37 | 58 | 36.8% | C | |
| SWE-Bench Verified | 73.4% | 44 | 105 | 58.6% | C | |
| Terminal-Bench 2.0 | 38.5% | 46 | 49 | 6.3% | C | |
| Humanity's Last Exam | 22.1% | 54 | 93 | 42.4% | C | |
| GPQA | 83.7% | 64 | 234 | 73.0% | C |
MiMo V2 Flash Arena Results
Preference and agent-evaluation results for the default version.
| webdev | overall | 86 | 1330.5 | 5,426 | N/A | |
| webdev | overall | 92 | 1291.5 | 1,665 | N/A | |
| text factuality | overall | 106 | 1422.1 | 45,951 | N/A | |
| text | overall | 117 | 1411.1 | 46,632 | N/A | |
| text factuality | overall | 122 | 1410.3 | 10,904 | N/A | |
| text | overall | 137 | 1394.5 | 10,986 | N/A | |
| text style control | overall | 148 | 1392.4 | 46,632 | N/A | |
| text style control | overall | 158 | 1386.4 | 10,986 | N/A |
MiMo V2 Flash Runtime Performance
Provider-specific output speed and catalog latency for MiMo-V2-Flash. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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 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, $0.30 output per 1M via ZenMux
- Tracked offerings
- 6
| ZenMux | xiaomi/mimo-v2-flash | global | $0.10 | $0.30 | 262.1K | |
| Hugging Face | XiaomiMiMo/MiMo-V2-Flash | global | $0.10 | $0.30 | 262.1K | |
| Qiniu | mimo-v2-flash | global | $0.10 | $0.30 | 256K | |
| Qiniu | xiaomi/mimo-v2-flash | global | $0.10 | $0.30 | 256K | |
| Meganova | XiaomiMiMo/MiMo-V2-Flash | global | $0.10 | $0.30 | 262.1K | |
| Xiaomi | mimo-v2-flash | global | $0.14 | $0.28 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
MiMo V2 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| MiMo-V2-Flash | 51.3 | 309B | 262.1K | 65.5K | Yes | MIT |
What is MiMo V2 Flash?
Key information about MiMo V2 Flash and its available data.
MiMo-V2-Flash is a powerful, efficient, and ultra-fast foundation language model that excels in reasoning, coding, and agentic scenarios.
It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, featuring a hybrid attention architecture with sliding-window and full attention (5:1 ratio, 128-token window). Delivers 150 tokens/sec inference with 256k context window.
Data as of 2026-08-11.
MiMo V2 Flash vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to MiMo V2 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XI
MiMo V2 Omni
Xiaomi
XI
MiMo V2.5 Pro
Xiaomi
XI
MiMo
Xiaomi
XI
MiMo V2 Pro
Xiaomi
XA
Grok 4.1 Thinking
xAI
GO
Google
Gemini 3.1 Flash Lite
FAQ
Common questions about MiMo V2 Flash.
When was MiMo V2 Flash released?
MiMo V2 Flash's default version was released on Dec 16, 2025.
How much does MiMo V2 Flash cost?
MiMo V2 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 $0.30 output via ZenMux.
Who created MiMo V2 Flash?
MiMo V2 Flash was created by Xiaomi.
What is the context window for MiMo V2 Flash?
The default version has a 262.1K token context window.
Is MiMo V2 Flash open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiMo V2 Flash?
6 provider offerings are linked to the default version.
What models should I compare MiMo V2 Flash with?
Nearby ranked alternatives include Claude Opus 4.1, Qwen3.5 35B A3B, Gemini 3.1 Flash Lite.