GeekRadar / The comparison desk
COMPARE.
AI models
thinky

inkling

Model evaluation

Capability & preference

Human preference · Arena

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

inkling 1441.4 inkling · 95% interval 1437.1–1445.7 · 40,648 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

inkling

1,491.60 rating

Confidence interval: 1,480.70 – 1,502.50

3197 votes

Category
chinese
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

inkling

1,465.43 rating

Confidence interval: 1,458.85 – 1,472.00

11078 votes

Category
coding
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

inkling

1,387.24 rating

Confidence interval: 1,379.78 – 1,394.69

8748 votes

Category
creative_writing
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

inkling

1,442.30 rating

Confidence interval: 1,436.61 – 1,447.99

16677 votes

Category
english
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

inkling

1,436.19 rating

Confidence interval: 1,430.59 – 1,441.78

29977 votes

Category
exclude_ties
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

inkling

1,465.10 rating

Confidence interval: 1,456.04 – 1,474.16

4821 votes

Category
expert
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

inkling

1,453.66 rating

Confidence interval: 1,435.79 – 1,471.54

1281 votes

Category
french
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

inkling

1,446.59 rating

Confidence interval: 1,422.62 – 1,470.56

627 votes

Category
german
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

inkling

1,451.40 rating

Confidence interval: 1,446.39 – 1,456.40

26664 votes

Category
hard_prompts
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

inkling

1,449.39 rating

Confidence interval: 1,442.76 – 1,456.02

10833 votes

Category
hard_prompts_english
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

inkling

1,439.22 rating

Confidence interval: 1,431.75 – 1,446.70

7568 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

inkling

1,392.58 rating

Confidence interval: 1,385.67 – 1,399.49

10607 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

inkling

1,448.12 rating

Confidence interval: 1,437.38 – 1,458.86

3363 votes

Category
industry_legal_and_government
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

inkling

1,455.15 rating

Confidence interval: 1,447.34 – 1,462.97

6689 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

inkling

1,459.74 rating

Confidence interval: 1,446.78 – 1,472.69

2255 votes

Category
industry_mathematical
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

inkling

1,447.80 rating

Confidence interval: 1,436.00 – 1,459.60

2766 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

inkling

1,465.18 rating

Confidence interval: 1,459.39 – 1,470.97

15820 votes

Category
industry_software_and_it_services
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

inkling

1,403.17 rating

Confidence interval: 1,396.44 – 1,409.89

11160 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

inkling

1,424.89 rating

Confidence interval: 1,418.87 – 1,430.92

14605 votes

Category
instruction_following
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

inkling

1,426.05 rating

Confidence interval: 1,400.84 – 1,451.26

638 votes

Category
japanese
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

inkling

1,403.18 rating

Confidence interval: 1,380.79 – 1,425.56

755 votes

Category
korean
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

inkling

1,433.58 rating

Confidence interval: 1,427.87 – 1,439.29

19084 votes

Category
longer_query
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

inkling

1,477.32 rating

Confidence interval: 1,463.54 – 1,491.10

1845 votes

Category
math
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

inkling

1,437.44 rating

Confidence interval: 1,429.31 – 1,445.57

6369 votes

Category
multi_turn
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

inkling

1,433.00 rating

Confidence interval: 1,427.94 – 1,438.07

23960 votes

Category
non_english
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

inkling

1,441.38 rating

Confidence interval: 1,437.09 – 1,445.68

40648 votes

Category
overall
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

inkling

1,452.62 rating

Confidence interval: 1,428.83 – 1,476.41

604 votes

Category
polish
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

inkling

1,429.44 rating

Confidence interval: 1,420.43 – 1,438.46

4822 votes

Category
russian
Evaluated configuration
inkling
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

inkling

1,446.96 rating

Confidence interval: 1,429.58 – 1,464.33

1269 votes

Category
spanish
Evaluated configuration
inkling
Evaluation type
human preference

Run it locally

Inference · memory estimate

inkling

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0