GeekRadar / The comparison desk
COMPARE.
AI models
xiaomi

MiMo-V2-Flash (Non-Thinking)

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

MiMo-V2-Flash (Non-Thinking) 1410.9 MiMo-V2-Flash (Non-Thinking) · 95% interval 1407.5–1414.4 · 48,060 votes · 2026-10-28

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,462.25 rating

Confidence interval: 1,451.97 – 1,472.54

3374 votes

Category
chinese
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,442.52 rating

Confidence interval: 1,436.66 – 1,448.37

12444 votes

Category
coding
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,375.86 rating

Confidence interval: 1,368.58 – 1,383.14

7338 votes

Category
creative_writing
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,429.53 rating

Confidence interval: 1,424.71 – 1,434.34

19927 votes

Category
english
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,396.16 rating

Confidence interval: 1,391.42 – 1,400.90

34717 votes

Category
exclude_ties
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,425.22 rating

Confidence interval: 1,415.78 – 1,434.66

4030 votes

Category
expert
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,419.19 rating

Confidence interval: 1,402.08 – 1,436.30

1334 votes

Category
french
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,384.73 rating

Confidence interval: 1,363.43 – 1,406.03

783 votes

Category
german
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,419.80 rating

Confidence interval: 1,415.52 – 1,424.09

29148 votes

Category
hard_prompts
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,435.68 rating

Confidence interval: 1,429.82 – 1,441.54

12286 votes

Category
hard_prompts_english
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,402.29 rating

Confidence interval: 1,395.75 – 1,408.83

9217 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,375.52 rating

Confidence interval: 1,368.89 – 1,382.16

9173 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,410.05 rating

Confidence interval: 1,399.89 – 1,420.21

3491 votes

Category
industry_legal_and_government
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,422.64 rating

Confidence interval: 1,415.70 – 1,429.57

7881 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,410.80 rating

Confidence interval: 1,398.86 – 1,422.74

2531 votes

Category
industry_mathematical
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,413.14 rating

Confidence interval: 1,402.57 – 1,423.70

3319 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,442.67 rating

Confidence interval: 1,437.67 – 1,447.67

18261 votes

Category
industry_software_and_it_services
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,383.63 rating

Confidence interval: 1,377.51 – 1,389.75

10921 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,392.56 rating

Confidence interval: 1,387.12 – 1,397.99

14750 votes

Category
instruction_following
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,325.49 rating

Confidence interval: 1,296.02 – 1,354.96

444 votes

Category
japanese
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,359.03 rating

Confidence interval: 1,337.25 – 1,380.81

775 votes

Category
korean
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,409.25 rating

Confidence interval: 1,403.88 – 1,414.61

16447 votes

Category
longer_query
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,395.56 rating

Confidence interval: 1,384.70 – 1,406.42

2983 votes

Category
math
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,403.80 rating

Confidence interval: 1,396.94 – 1,410.65

8514 votes

Category
multi_turn
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,391.50 rating

Confidence interval: 1,387.25 – 1,395.75

28133 votes

Category
non_english
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,410.93 rating

Confidence interval: 1,407.50 – 1,414.37

48060 votes

Category
overall
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,406.37 rating

Confidence interval: 1,389.55 – 1,423.18

1205 votes

Category
polish
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,387.37 rating

Confidence interval: 1,379.71 – 1,395.02

6206 votes

Category
russian
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

MiMo-V2-Flash (Non-Thinking)

1,421.10 rating

Confidence interval: 1,405.37 – 1,436.83

1528 votes

Category
spanish
Evaluated configuration
MiMo-V2-Flash (Non-Thinking)
Evaluation type
human preference

Run it locally

Inference · memory estimate

MiMo-V2-Flash (Non-Thinking)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
MIT