GeekRadar / The comparison desk
COMPARE.
AI models
moonshot

Kimi K2 Preview (0711)

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 Preview (0711) 1370.7 Kimi K2 Preview (0711) · 95% interval 1365.9–1375.6 · 27,139 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

Kimi K2 Preview (0711)

1,400.66 rating

Confidence interval: 1,387.33 – 1,413.98

2082 votes

Category
chinese
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,376.58 rating

Confidence interval: 1,368.14 – 1,385.02

5192 votes

Category
coding
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,323.34 rating

Confidence interval: 1,313.01 – 1,333.66

3412 votes

Category
creative_writing
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,376.56 rating

Confidence interval: 1,370.24 – 1,382.88

11713 votes

Category
english
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,337.85 rating

Confidence interval: 1,331.45 – 1,344.24

19592 votes

Category
exclude_ties
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,345.97 rating

Confidence interval: 1,330.53 – 1,361.42

1489 votes

Category
expert
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,373.24 rating

Confidence interval: 1,343.77 – 1,402.72

407 votes

Category
french
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,374.21 rating

Confidence interval: 1,351.12 – 1,397.30

653 votes

Category
german
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,365.44 rating

Confidence interval: 1,359.16 – 1,371.72

12091 votes

Category
hard_prompts
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,369.61 rating

Confidence interval: 1,361.18 – 1,378.04

5392 votes

Category
hard_prompts_english
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,342.65 rating

Confidence interval: 1,333.52 – 1,351.77

4543 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,332.40 rating

Confidence interval: 1,323.73 – 1,341.08

4812 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,352.95 rating

Confidence interval: 1,338.46 – 1,367.44

1741 votes

Category
industry_legal_and_government
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,364.12 rating

Confidence interval: 1,354.87 – 1,373.38

4368 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,356.86 rating

Confidence interval: 1,342.03 – 1,371.70

1567 votes

Category
industry_mathematical
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,367.54 rating

Confidence interval: 1,352.78 – 1,382.30

1693 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,384.17 rating

Confidence interval: 1,377.26 – 1,391.08

8968 votes

Category
industry_software_and_it_services
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,328.32 rating

Confidence interval: 1,320.30 – 1,336.34

5976 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,324.22 rating

Confidence interval: 1,316.58 – 1,331.87

6768 votes

Category
instruction_following
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,335.91 rating

Confidence interval: 1,315.52 – 1,356.30

903 votes

Category
japanese
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,286.77 rating

Confidence interval: 1,262.37 – 1,311.17

651 votes

Category
korean
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,325.72 rating

Confidence interval: 1,317.48 – 1,333.95

5545 votes

Category
longer_query
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,367.18 rating

Confidence interval: 1,353.15 – 1,381.20

1696 votes

Category
math
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,370.70 rating

Confidence interval: 1,361.65 – 1,379.74

4554 votes

Category
multi_turn
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,357.70 rating

Confidence interval: 1,351.91 – 1,363.49

15414 votes

Category
non_english
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,370.74 rating

Confidence interval: 1,365.87 – 1,375.61

27139 votes

Category
overall
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,371.95 rating

Confidence interval: 1,358.91 – 1,385.00

2271 votes

Category
polish
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,361.27 rating

Confidence interval: 1,347.93 – 1,374.60

1824 votes

Category
russian
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Kimi K2 Preview (0711)

1,329.63 rating

Confidence interval: 1,304.63 – 1,354.62

618 votes

Category
spanish
Evaluated configuration
Kimi K2 Preview (0711)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Kimi K2 Preview (0711)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Modified MIT