#63
XI
MiMo V2 Flash
Xiaomi
55.9 LLMBoard
Xiaomi model product
MiMo-V2.5 is Xiaomi's native omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window. Built on the MiMo-V2-Flash backbone, it adds dedicated vision and audio encoders for text, image, video, and audio understanding, and is post-trained with SFT, agentic reinforcement learning, and Multi-Teacher On-Policy Distillation for multimodal perception, long-context reasoning, and agentic workflows.
Updated Aug 10, 2026. Default version: MiMo-V2.5
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.
| vision style control | chinese | 25 | 1315.5 | 981 | N/A | |
| vision | chinese | 28 | 1326.2 | 981 | N/A | |
| text factuality | korean | 30 | 1376.8 | 422 | N/A | |
| text factuality | industry mathematical | 33 | 1451.7 | 1,925 | N/A | |
| text factuality | french | 35 | 1473.5 | 1,360 | N/A | |
| text factuality | math | 35 | 1447.7 | 1,891 | N/A | |
| vision | entity recognition | 36 | 1195.9 | 143 | N/A | |
| vision | english | 38 | 1263.4 | 8,578 | N/A | |
| vision style control | entity recognition | 38 | 1171.5 | 143 | N/A | |
| text factuality | japanese | 39 | 1335.5 | 364 | N/A | |
| vision | diagram | 40 | 1274.1 | 5,611 | N/A | |
| text | hard prompts english | 42 | 1461.6 | 14,080 | N/A | |
| text factuality | spanish | 43 | 1431.2 | 1,030 | N/A | |
| vision | ocr | 43 | 1261.9 | 15,030 | N/A | |
| vision style control | diagram | 43 | 1270.5 | 5,611 | N/A | |
| text factuality | coding | 44 | 1504.1 | 12,146 | N/A | |
| vision | humor | 45 | 1232.8 | 752 | N/A | |
| vision | overall | 46 | 1251.4 | 20,781 | N/A | |
| vision style control | english | 46 | 1244.3 | 8,578 | N/A | |
| text factuality | chinese | 47 | 1486.2 | 1,724 | N/A | |
| text factuality | hard prompts english | 47 | 1482.0 | 13,528 | N/A | |
| vision style control | humor | 47 | 1220.2 | 752 | N/A | |
| vision style control | ocr | 47 | 1252.9 | 15,030 | N/A | |
| webdev | webdev-react | 47 | 1426.3 | 8,771 | N/A | |
| text factuality | industry software and it services | 48 | 1487.1 | 17,742 | N/A | |
| vision | homework | 48 | 1267.2 | 3,082 | N/A | |
| vision style control | homework | 48 | 1260.3 | 3,082 | N/A | |
| webdev | overall | 48 | 1436.9 | 10,952 | N/A | |
| webdev | webdev | 48 | 1436.9 | 10,952 | N/A | |
| text factuality | expert | 49 | 1478.7 | 3,533 | N/A | |
| vision style control | overall | 50 | 1237.7 | 20,781 | N/A | |
| text | coding | 51 | 1469.3 | 12,790 | N/A | |
| text | industry business and management and financial operations | 51 | 1433.2 | 9,008 | N/A | |
| text | instruction following | 51 | 1434.1 | 14,726 | N/A | |
| text | longer query | 52 | 1445.5 | 19,336 | N/A | |
| text factuality | longer query | 52 | 1462.3 | 18,822 | N/A | |
| text | expert | 53 | 1462.7 | 4,248 | N/A | |
| text | industry mathematical | 53 | 1450.5 | 2,398 | N/A | |
| text factuality | instruction following | 53 | 1443.3 | 14,157 | N/A | |
| text | hard prompts | 54 | 1449.9 | 29,501 | N/A | |
| vision | creative writing vision | 54 | 1226.5 | 1,122 | N/A | |
| text | industry software and it services | 55 | 1462.6 | 18,028 | N/A | |
| text factuality | industry business and management and financial operations | 55 | 1452.2 | 8,000 | N/A | |
| webdev | webdev-html | 55 | 1426.0 | 1,279 | N/A | |
| vision style control | creative writing vision | 56 | 1209.5 | 1,122 | N/A | |
| text factuality | english | 58 | 1456.4 | 20,036 | N/A | |
| text factuality | hard prompts | 58 | 1469.7 | 29,460 | N/A | |
| text style control | industry mathematical | 58 | 1455.4 | 2,398 | N/A | |
| text factuality | multi turn | 59 | 1457.8 | 6,781 | N/A | |
| text | english | 61 | 1447.5 | 20,068 | N/A | |
| text | multi turn | 62 | 1444.3 | 7,841 | N/A | |
| text style control | expert | 65 | 1474.3 | 4,248 | N/A | |
| text | math | 66 | 1438.8 | 2,318 | N/A | |
| text style control | longer query | 66 | 1452.8 | 19,336 | N/A | |
| text factuality | industry entertainment and sports and media | 67 | 1411.4 | 8,958 | N/A | |
| text style control | chinese | 67 | 1484.6 | 2,113 | N/A | |
| text style control | hard prompts english | 67 | 1472.2 | 14,080 | N/A | |
| text style control | math | 67 | 1441.4 | 2,318 | N/A | |
| text style control | english | 69 | 1453.0 | 20,068 | N/A | |
| text factuality | industry life and physical and social science | 70 | 1462.3 | 6,206 | N/A | |
| text style control | coding | 71 | 1491.0 | 12,790 | N/A | |
| text style control | multi turn | 71 | 1450.6 | 7,841 | N/A | |
| text | chinese | 73 | 1471.5 | 2,113 | N/A | |
| text style control | hard prompts | 73 | 1462.0 | 29,501 | N/A | |
| text style control | industry business and management and financial operations | 73 | 1442.7 | 9,008 | N/A | |
| text style control | industry software and it services | 73 | 1479.3 | 18,028 | N/A | |
| text style control | instruction following | 73 | 1431.7 | 14,726 | N/A | |
| text factuality | industry writing and literature and language | 75 | 1419.1 | 10,014 | N/A | |
| text | french | 76 | 1445.0 | 1,734 | N/A | |
| text factuality | overall | 77 | 1439.1 | 44,129 | N/A | |
| text factuality | industry legal and government | 77 | 1442.9 | 2,887 | N/A | |
| text | overall | 80 | 1427.6 | 44,200 | N/A | |
| text factuality | exclude ties | 81 | 1434.5 | 33,819 | N/A | |
| text factuality | industry medicine and healthcare | 81 | 1455.6 | 2,494 | N/A | |
| text | exclude ties | 82 | 1417.1 | 33,875 | N/A | |
| text | industry entertainment and sports and media | 82 | 1398.1 | 9,591 | N/A | |
| text factuality | creative writing | 82 | 1405.3 | 6,275 | N/A | |
| text style control | industry life and physical and social science | 82 | 1453.4 | 7,119 | N/A | |
| text | industry writing and literature and language | 83 | 1407.9 | 10,640 | N/A | |
| text factuality | russian | 83 | 1420.3 | 3,914 | N/A | |
| text style control | french | 83 | 1452.9 | 1,734 | N/A | |
| text style control | industry entertainment and sports and media | 84 | 1402.3 | 9,591 | N/A | |
| text style control | industry writing and literature and language | 84 | 1411.4 | 10,640 | N/A | |
| text | industry life and physical and social science | 85 | 1439.8 | 7,119 | N/A | |
| text style control | overall | 85 | 1434.0 | 44,200 | N/A | |
| text style control | exclude ties | 85 | 1427.7 | 33,875 | N/A | |
| text style control | polish | 85 | 1419.5 | 929 | N/A | |
| text style control | german | 87 | 1421.8 | 749 | N/A | |
| text | polish | 88 | 1413.0 | 929 | N/A | |
| text factuality | non english | 90 | 1418.2 | 24,086 | N/A | |
| text style control | industry medicine and healthcare | 91 | 1447.9 | 3,106 | N/A | |
| text | german | 94 | 1409.0 | 749 | N/A | |
| text | korean | 94 | 1363.2 | 786 | N/A | |
| text style control | korean | 94 | 1371.0 | 786 | N/A | |
| text style control | non english | 94 | 1411.2 | 24,131 | N/A | |
| text | creative writing | 96 | 1391.8 | 7,236 | N/A | |
| text | spanish | 96 | 1413.6 | 1,362 | N/A | |
| text | industry medicine and healthcare | 98 | 1429.0 | 3,106 | N/A | |
| text style control | spanish | 99 | 1412.2 | 1,362 | N/A | |
| text style control | creative writing | 100 | 1394.0 | 7,236 | 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-v2.5 | global | N/A | N/A | 1M | |
| Xiaomi Token Plan (Europe) | mimo-v2.5 | global | N/A | N/A | 1M | |
| Xiaomi Token Plan (Singapore) | mimo-v2.5 | global | N/A | N/A | 1M | |
| OpenCode Go | mimo-v2.5 | global | $0.14 | $0.28 | 1M | |
| LLM Gateway | mimo-v2.5 | global | $0.14 | $0.28 | 1M | |
| Xiaomi | mimo-v2.5 | global | $0.14 | $0.28 | 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-V2.5 | N/A | 310.8B | 1M | 131.1K | Yes | MIT |
A concise description based on the published model registry.
MiMo-V2.5 is Xiaomi's native omnimodal sparse Mixture-of-Experts model with 310B total parameters, 15B activated parameters, and a 1M-token context window. Built on the MiMo-V2-Flash backbone, it adds dedicated vision and audio encoders for text, image, video, and audio understanding, and is post-trained with SFT, agentic reinforcement learning, and Multi-Teacher On-Policy Distillation for multimodal perception, long-context reasoning, and agentic workflows.
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.
MiMo's default version was released on Apr 22, 2026.
MiMo'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 $0.14 input and $0.28 output via OpenCode Go.
MiMo is published under Xiaomi in the model registry.
The default version has a 1M token context window.
Yes. The default version is marked as open weight under MIT.
6 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.