GeekRadar / The comparison desk
COMPARE.
AI models
moonshot

kimi-k2-0711-preview

Model evaluation

Capability & preference

Human preference · Arena

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

kimi-k2-0711-preview 1370.7 kimi-k2-0711-preview · 95% interval 1365.8–1375.6 · 27,146 votes · 2026-10-15

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 · 2026-10-15 · rating

kimi-k2-0711-preview

1,400.85 rating

Confidence interval: 1,387.53 – 1,414.17

2080 votes

Category
chinese
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,376.67 rating

Confidence interval: 1,368.23 – 1,385.10

5194 votes

Category
coding
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,323.22 rating

Confidence interval: 1,312.90 – 1,333.54

3413 votes

Category
creative_writing
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,376.54 rating

Confidence interval: 1,370.21 – 1,382.86

11717 votes

Category
english
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,337.82 rating

Confidence interval: 1,331.43 – 1,344.22

19595 votes

Category
exclude_ties
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,346.18 rating

Confidence interval: 1,330.72 – 1,361.64

1487 votes

Category
expert
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,372.81 rating

Confidence interval: 1,343.33 – 1,402.29

407 votes

Category
french
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,373.51 rating

Confidence interval: 1,350.43 – 1,396.59

652 votes

Category
german
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,365.37 rating

Confidence interval: 1,359.09 – 1,371.66

12092 votes

Category
hard_prompts
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,369.53 rating

Confidence interval: 1,361.10 – 1,377.96

5392 votes

Category
hard_prompts_english
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,342.66 rating

Confidence interval: 1,333.53 – 1,351.78

4545 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,332.31 rating

Confidence interval: 1,323.64 – 1,340.99

4811 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,352.92 rating

Confidence interval: 1,338.43 – 1,367.41

1742 votes

Category
industry_legal_and_government
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,364.14 rating

Confidence interval: 1,354.89 – 1,373.39

4368 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,356.90 rating

Confidence interval: 1,342.06 – 1,371.73

1567 votes

Category
industry_mathematical
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,367.49 rating

Confidence interval: 1,352.73 – 1,382.25

1692 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,384.17 rating

Confidence interval: 1,377.26 – 1,391.08

8968 votes

Category
industry_software_and_it_services
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,328.19 rating

Confidence interval: 1,320.18 – 1,336.20

5977 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,324.13 rating

Confidence interval: 1,316.49 – 1,331.78

6770 votes

Category
instruction_following
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,335.97 rating

Confidence interval: 1,315.61 – 1,356.33

904 votes

Category
japanese
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,287.45 rating

Confidence interval: 1,263.02 – 1,311.88

651 votes

Category
korean
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,325.54 rating

Confidence interval: 1,317.30 – 1,333.78

5545 votes

Category
longer_query
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,366.81 rating

Confidence interval: 1,352.79 – 1,380.84

1696 votes

Category
math
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,370.54 rating

Confidence interval: 1,361.49 – 1,379.58

4555 votes

Category
multi_turn
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,357.68 rating

Confidence interval: 1,351.89 – 1,363.46

15417 votes

Category
non_english
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,370.69 rating

Confidence interval: 1,365.82 – 1,375.56

27146 votes

Category
overall
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,371.90 rating

Confidence interval: 1,358.85 – 1,384.95

2270 votes

Category
polish
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,360.76 rating

Confidence interval: 1,347.43 – 1,374.10

1824 votes

Category
russian
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

kimi-k2-0711-preview

1,329.71 rating

Confidence interval: 1,304.75 – 1,354.68

619 votes

Category
spanish
Evaluated configuration
kimi-k2-0711-preview
Evaluation type
human preference

Run it locally

Inference · memory estimate

kimi-k2-0711-preview

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Modified MIT