Xiaomi model product
MiMo-V2-Pro is Xiaomi's flagship foundation model built for real-world agentic workloads.
Updated Aug 12, 2026. Default version: MiMo-V2-Pro
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for MiMo-V2-Pro.
| PinchBench | 81.0% | 03 | 4 | 33.3% | C | |
| DeepSearchQA | 86.7% | 05 | 9 | 50.0% | C | |
| Tau2 Telecom | 96.8% | 08 | 35 | 79.4% | C | |
| Claw-Eval | 61.5% | 09 | 13 | 33.3% | C | |
| SWE-bench Multilingual | 71.7% | 16 | 34 | 54.5% | C | |
| SWE-Bench Verified | 78.0% | 21 | 105 | 80.8% | C | |
| Terminal-Bench 2.0 | 57.1% | 25 | 49 | 50.0% | C |
Preference and agent-evaluation results for the default version.
| webdev | overall | 52 | 1433.5 | 6,955 | N/A | |
| text style control | overall | 64 | 1448.3 | 24,421 | N/A | |
| text | overall | 69 | 1436.2 | 24,421 | N/A | |
| text factuality | overall | 70 | 1443.6 | 24,386 | N/A |
Provider-specific output speed and catalog latency for MiMo-V2-Pro. 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.
Official vendor API pricing appears first, followed by individual provider offers.
| Xiaomi Token Plan (China) | mimo-v2-pro | global | N/A | N/A | 1M | |
| Xiaomi Token Plan (Europe) | mimo-v2-pro | global | N/A | N/A | 1M | |
| Xiaomi Token Plan (Singapore) | mimo-v2-pro | global | N/A | N/A | 1M | |
| Xiaomi | mimo-v2-pro | global | $0.435 | $0.87 | 1M | |
| OpenCode Go | mimo-v2-pro | global | $1 | $3 | 1M | |
| ZenMux | xiaomi/mimo-v2-pro | global | $1 | $3 | 1M | |
| Abacus | mimo-v2-pro | global | $1 | $3 | 1M | |
| NovitaAI | xiaomimimo/mimo-v2-pro | global | $2 | $6 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| MiMo-V2-Pro | 64.0 | 1T | 1M | 131.1K | No | Proprietary |
Key information about MiMo V2 Pro and its available data.
MiMo-V2-Pro is Xiaomi's flagship foundation model built for real-world agentic workloads. A Mixture-of-Experts model with over 1T total parameters and 42B active, roughly 3x larger than MiMo-V2-Flash. Inherits the Hybrid Attention mechanism with a 7:1 ratio and supports up to 1M-token context.
Optimized for coding and agent tasks through post-training scaling across diverse agent scenarios, with native support for complex tool calling and multi-step reasoning.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about MiMo V2 Pro.
MiMo V2 Pro's default version was released on Mar 18, 2026.
MiMo V2 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 $1 input and $3 output via OpenCode Go.
MiMo V2 Pro was created by Xiaomi.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
8 provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen3.5 397B A17B, Kimi K2.5, Gemini 3 Flash.