#63
XI
MiMo V2 Flash
Xiaomi
55.9 LLMBoard
Xiaomi model product
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.
Updated Aug 10, 2026. Default version: MiMo-V2-Pro
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
No published version under this unique model currently has enough benchmark coverage to calculate a score.
Published benchmark records for the scored version currently unavailable.
No published benchmark result is linked to the scored version.
Preference and agent-evaluation signals from published Arena datasets.
| text factuality | hard prompts english | 31 | 1495.2 | 6,295 | N/A | |
| text | hard prompts english | 32 | 1472.6 | 7,437 | N/A | |
| text factuality | expert | 34 | 1488.8 | 1,457 | N/A | |
| text | expert | 35 | 1478.6 | 2,005 | N/A | |
| text | french | 37 | 1468.4 | 894 | N/A | |
| text | multi turn | 37 | 1459.5 | 4,381 | N/A | |
| text | spanish | 37 | 1455.1 | 776 | N/A | |
| text style control | expert | 38 | 1492.4 | 2,005 | N/A | |
| text | instruction following | 40 | 1443.8 | 7,900 | N/A | |
| text factuality | coding | 40 | 1506.0 | 5,589 | N/A | |
| text factuality | math | 40 | 1444.2 | 1,165 | N/A | |
| text style control | hard prompts english | 40 | 1489.0 | 7,437 | N/A | |
| text | industry business and management and financial operations | 42 | 1440.2 | 4,785 | N/A | |
| text | industry mathematical | 42 | 1462.7 | 1,434 | N/A | |
| text | longer query | 42 | 1455.4 | 9,283 | N/A | |
| text factuality | english | 42 | 1464.0 | 10,877 | N/A | |
| text style control | french | 42 | 1479.6 | 894 | N/A | |
| text | hard prompts | 43 | 1457.7 | 15,577 | N/A | |
| text factuality | instruction following | 43 | 1450.7 | 6,632 | N/A | |
| text | coding | 44 | 1476.3 | 6,872 | N/A | |
| text style control | industry mathematical | 44 | 1469.5 | 1,434 | N/A | |
| text style control | korean | 46 | 1415.2 | 454 | N/A | |
| text | english | 47 | 1453.5 | 10,955 | N/A | |
| text factuality | longer query | 47 | 1466.0 | 8,092 | N/A | |
| text | industry software and it services | 48 | 1467.7 | 9,750 | N/A | |
| text factuality | industry entertainment and sports and media | 48 | 1428.8 | 3,562 | N/A | |
| text style control | industry life and physical and social science | 48 | 1479.0 | 3,852 | N/A | |
| webdev | webdev-html | 48 | 1439.2 | 793 | N/A | |
| webdev | webdev-react | 48 | 1425.2 | 5,969 | N/A | |
| text style control | longer query | 49 | 1466.6 | 9,283 | N/A | |
| text style control | spanish | 49 | 1453.0 | 776 | N/A | |
| text factuality | hard prompts | 50 | 1472.8 | 15,535 | N/A | |
| text factuality | industry business and management and financial operations | 50 | 1455.1 | 3,573 | N/A | |
| text factuality | industry software and it services | 50 | 1486.3 | 9,028 | N/A | |
| text style control | multi turn | 50 | 1469.5 | 4,381 | N/A | |
| text | industry life and physical and social science | 51 | 1457.1 | 3,852 | N/A | |
| text factuality | industry life and physical and social science | 51 | 1472.1 | 2,870 | N/A | |
| text factuality | multi turn | 51 | 1461.1 | 3,304 | N/A | |
| text | industry entertainment and sports and media | 52 | 1414.9 | 4,638 | N/A | |
| text | korean | 52 | 1398.3 | 454 | N/A | |
| webdev | overall | 52 | 1433.0 | 6,844 | N/A | |
| webdev | webdev | 52 | 1433.0 | 6,844 | N/A | |
| text | math | 53 | 1447.9 | 1,606 | N/A | |
| text factuality | creative writing | 53 | 1424.9 | 2,620 | N/A | |
| text style control | coding | 53 | 1502.9 | 6,872 | N/A | |
| text style control | english | 53 | 1464.9 | 10,955 | N/A | |
| text style control | industry software and it services | 54 | 1490.2 | 9,750 | N/A | |
| text style control | instruction following | 54 | 1444.7 | 7,900 | N/A | |
| text factuality | industry writing and literature and language | 55 | 1431.9 | 4,337 | N/A | |
| text style control | hard prompts | 55 | 1475.7 | 15,577 | N/A | |
| text style control | industry business and management and financial operations | 55 | 1455.7 | 4,785 | N/A | |
| text | creative writing | 56 | 1415.5 | 3,535 | N/A | |
| text | industry writing and literature and language | 56 | 1423.5 | 5,576 | N/A | |
| text style control | math | 56 | 1451.9 | 1,606 | N/A | |
| text | industry legal and government | 58 | 1446.7 | 1,732 | N/A | |
| text style control | industry entertainment and sports and media | 59 | 1425.1 | 4,638 | N/A | |
| text style control | industry writing and literature and language | 60 | 1431.6 | 5,576 | N/A | |
| text factuality | industry legal and government | 61 | 1455.7 | 1,261 | N/A | |
| text style control | creative writing | 62 | 1424.6 | 3,535 | N/A | |
| text factuality | industry medicine and healthcare | 63 | 1465.9 | 1,209 | N/A | |
| text style control | overall | 65 | 1448.0 | 24,211 | N/A | |
| text style control | japanese | 65 | 1405.9 | 161 | N/A | |
| text style control | exclude ties | 66 | 1448.6 | 18,333 | N/A | |
| text style control | industry legal and government | 67 | 1457.8 | 1,732 | N/A | |
| text style control | polish | 67 | 1443.3 | 559 | N/A | |
| text style control | industry medicine and healthcare | 68 | 1468.2 | 1,683 | N/A | |
| text | overall | 70 | 1435.8 | 24,211 | N/A | |
| text factuality | exclude ties | 70 | 1441.6 | 18,303 | N/A | |
| text factuality | overall | 71 | 1443.3 | 24,176 | N/A | |
| text | exclude ties | 72 | 1429.6 | 18,333 | N/A | |
| text | polish | 73 | 1425.2 | 559 | N/A | |
| text factuality | russian | 73 | 1434.1 | 2,049 | N/A | |
| text style control | chinese | 73 | 1481.8 | 1,260 | N/A | |
| text style control | non english | 73 | 1428.6 | 13,256 | N/A | |
| text style control | russian | 74 | 1439.3 | 2,761 | N/A | |
| text | russian | 76 | 1424.0 | 2,761 | N/A | |
| text | non english | 77 | 1416.0 | 13,256 | N/A | |
| text factuality | non english | 79 | 1421.7 | 13,222 | N/A | |
| text style control | german | 79 | 1432.2 | 431 | N/A | |
| text | japanese | 82 | 1375.6 | 161 | N/A | |
| text | german | 84 | 1419.1 | 431 | N/A | |
| text | industry medicine and healthcare | 86 | 1438.7 | 1,683 | N/A | |
| text | chinese | 101 | 1455.6 | 1,260 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| 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 | |
| Abacus | mimo-v2-pro | global | $1 | $3 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| MiMo-V2-Pro | N/A | 1T | 1M | 131.1K | No | Proprietary |
A concise description based on the published model registry.
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.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Recommendations prioritize the same model type and family, then the closest published 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 is published under Xiaomi in the model registry.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
6 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.