MiMo-V2.6-Flash

XiaomiOpenMIT

MiMo-V2.6-Flash is a vision-language model from Xiaomi. It ranks 56 of 167 on LMArena’s overall vision board with 1260±9 from 6,906 votes. Its best category is Homework (#47 of 118). License: MIT.

Key figures

LMArena · Overall1260±9#56 / 167 · Votes 6,906
OCR1273±10#49 / 123 · Votes 4,763
Diagrams1266±15#59 / 123 · Votes 1,701
Homework1288±19#47 / 118 · Votes 1,016
Creative writing1236±26#62 / 106 · Votes 591
Humor1236±38#62 / 102 · Votes 277
English1274±14#44 / 167 · Votes 2,095
Chinese1346±34#27 / 135 · Votes 320
Developer
Xiaomi
License
MIT
First seen (our snapshots)
2026-10-26

No data: Captioning, Entity recognition.

Who it suits

  • Overall #56 of 167: upper half.
  • Strongest category: Homework (#47 of 118).
  • Open weights (MIT): you can self-host it.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
53Grok 4.20 Beta (Reasoning, 0309) xAI126326,586Proprietary+3
54Qwen3.5-397B-A17B Alibaba126233,611Apache 2.0+2
55Gemma 4 26B A4B Google126023,747Apache 2.0+0
56MiMo-V2.6-Flash Xiaomi12606,906MIT
57Grok 4.20 Multi-Agent Beta (0309) xAI125924,357Proprietary-1
58GPT-5.6 Luna (xHigh) OpenAI125611,071Proprietary-4
59Gemini 2.5 Flash Preview (09-2025) Google12534,780Proprietary-7

Alternatives · More from Xiaomi

#ModelScoreVotesLicense
47MiMo-V2.6-Pro Xiaomi12661,826MIT
65MiMo-V2.5 Xiaomi124829,427MIT
82MiMo-V2-Omni Xiaomi122810,599Proprietary

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129531,530MIT
34Kimi K2.6 Moonshot AI128216,265Modified MIT
36Gemma 4 31B Google127941,787Apache 2.0
37DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12794,247MIT
42Qwen3.8-27B Alibaba12709,632Apache 2.0

How to read these scores

  • If two scores differ by less than their ± intervals, the models are statistically close.
  • Each category board is computed independently; do not compare scores across categories.
  • Models with few votes move more; ranks of new entries may change.

FAQ

Where does MiMo-V2.6-Flash rank among vision models?

Overall rank 56 (1260); OCR rank 49 (1273); Diagrams rank 59 (1266); Homework rank 47 (1288); Creative writing rank 62 (1236); Humor rank 62 (1236); English rank 44 (1274); Chinese rank 27 (1346) (LMArena, data as of Nov 14, 2026).

How good is MiMo-V2.6-Flash at OCR?

MiMo-V2.6-Flash ranks 49 of 123 on LMArena’s OCR board with 1273 (4,763 votes).

Is MiMo-V2.6-Flash better with Chinese or English prompts?

Chinese board: #27 of 135 (1346); English board: #44 of 167 (1274). The boards are computed separately, so compare ranks rather than scores.

Is MiMo-V2.6-Flash open-weight?

LMArena lists its license as MIT, not proprietary; check the license text for commercial use.

How far is MiMo-V2.6-Flash from #1?

#1 overall is Claude Fable 5 (High) (1326); MiMo-V2.6-Flash has 1260, 66 points behind.

Sources

LMArena data published Nov 9, 2026.

Synced here Nov 14, 2026.

Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.