GeekRadar / The comparison desk
COMPARE.
AI models
ant-group

Ling-flash-2.0

Model evaluation

Capability & preference

Human preference · Arena

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

Ling-flash-2.0 1361.1 Ling-flash-2.0 · 95% interval 1353.9–1368.3 · 6,952 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

Ling-flash-2.0

1,417.64 rating

Confidence interval: 1,390.47 – 1,444.80

454 votes

Category
chinese
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,389.02 rating

Confidence interval: 1,374.51 – 1,403.54

1543 votes

Category
coding
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,287.16 rating

Confidence interval: 1,267.08 – 1,307.24

853 votes

Category
creative_writing
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,385.82 rating

Confidence interval: 1,375.44 – 1,396.20

3045 votes

Category
english
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,323.47 rating

Confidence interval: 1,313.31 – 1,333.63

4894 votes

Category
exclude_ties
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,353.66 rating

Confidence interval: 1,323.89 – 1,383.43

354 votes

Category
expert
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,362.74 rating

Confidence interval: 1,352.91 – 1,372.57

3462 votes

Category
hard_prompts
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,387.30 rating

Confidence interval: 1,373.03 – 1,401.56

1606 votes

Category
hard_prompts_english
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,357.14 rating

Confidence interval: 1,341.03 – 1,373.24

1320 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,294.70 rating

Confidence interval: 1,278.04 – 1,311.37

1202 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,363.39 rating

Confidence interval: 1,335.72 – 1,391.06

417 votes

Category
industry_legal_and_government
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,381.49 rating

Confidence interval: 1,363.40 – 1,399.57

1012 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,368.17 rating

Confidence interval: 1,339.80 – 1,396.54

378 votes

Category
industry_mathematical
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,358.11 rating

Confidence interval: 1,328.04 – 1,388.18

356 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,400.34 rating

Confidence interval: 1,388.83 – 1,411.85

2516 votes

Category
industry_software_and_it_services
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,295.28 rating

Confidence interval: 1,280.07 – 1,310.50

1478 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,318.35 rating

Confidence interval: 1,304.95 – 1,331.75

1838 votes

Category
instruction_following
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,333.00 rating

Confidence interval: 1,295.38 – 1,370.63

241 votes

Category
korean
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,324.11 rating

Confidence interval: 1,308.24 – 1,339.98

1290 votes

Category
longer_query
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,363.98 rating

Confidence interval: 1,337.33 – 1,390.62

450 votes

Category
math
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,323.01 rating

Confidence interval: 1,305.52 – 1,340.50

1118 votes

Category
multi_turn
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,334.86 rating

Confidence interval: 1,325.50 – 1,344.21

3907 votes

Category
non_english
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,361.11 rating

Confidence interval: 1,353.90 – 1,368.32

6952 votes

Category
overall
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,311.45 rating

Confidence interval: 1,278.32 – 1,344.59

326 votes

Category
polish
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,307.57 rating

Confidence interval: 1,281.45 – 1,333.69

475 votes

Category
russian
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Ling-flash-2.0

1,404.99 rating

Confidence interval: 1,369.02 – 1,440.95

277 votes

Category
spanish
Evaluated configuration
Ling-flash-2.0
Evaluation type
human preference

Run it locally

Inference · memory estimate

Ling-flash-2.0

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
MIT