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 1443.3 Inkling · 95% interval 1439.2–1447.4 · 50,175 votes · 2026-11-06

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 · 2026-11-06 · rating

Inkling

1,495.27 rating

Confidence interval: 1,485.31 – 1,505.22

3944 votes

Category
chinese
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Inkling

1,466.70 rating

Confidence interval: 1,460.53 – 1,472.88

13469 votes

Category
coding
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Inkling

1,394.91 rating

Confidence interval: 1,387.99 – 1,401.83

10965 votes

Category
creative_writing
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Inkling

1,443.00 rating

Confidence interval: 1,437.65 – 1,448.35

20220 votes

Category
english
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Inkling

1,439.00 rating

Confidence interval: 1,433.73 – 1,444.27

37221 votes

Category
exclude_ties
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Inkling

1,468.63 rating

Confidence interval: 1,460.18 – 1,477.07

5754 votes

Category
expert
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Inkling

1,462.18 rating

Confidence interval: 1,445.96 – 1,478.40

1631 votes

Category
french
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Inkling

1,442.24 rating

Confidence interval: 1,420.50 – 1,463.97

775 votes

Category
german
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Inkling

1,452.97 rating

Confidence interval: 1,448.24 – 1,457.69

32839 votes

Category
hard_prompts
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Inkling

1,449.67 rating

Confidence interval: 1,443.44 – 1,455.90

13189 votes

Category
hard_prompts_english
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Inkling

1,438.97 rating

Confidence interval: 1,432.01 – 1,445.93

9256 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 · 2026-11-06 · rating

Inkling

1,398.44 rating

Confidence interval: 1,392.01 – 1,404.88

13198 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Inkling

1,446.01 rating

Confidence interval: 1,436.10 – 1,455.92

4109 votes

Category
industry_legal_and_government
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Inkling

1,457.29 rating

Confidence interval: 1,450.03 – 1,464.56

8236 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Inkling

1,464.74 rating

Confidence interval: 1,452.81 – 1,476.67

2741 votes

Category
industry_mathematical
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Inkling

1,449.04 rating

Confidence interval: 1,438.19 – 1,459.90

3380 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Inkling

1,466.25 rating

Confidence interval: 1,460.82 – 1,471.68

19262 votes

Category
industry_software_and_it_services
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Inkling

1,409.52 rating

Confidence interval: 1,403.29 – 1,415.75

14079 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Inkling

1,429.06 rating

Confidence interval: 1,423.43 – 1,434.69

18110 votes

Category
instruction_following
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Inkling

1,433.11 rating

Confidence interval: 1,410.19 – 1,456.03

783 votes

Category
japanese
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Inkling

1,405.02 rating

Confidence interval: 1,384.33 – 1,425.71

910 votes

Category
korean
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Inkling

1,437.53 rating

Confidence interval: 1,432.18 – 1,442.87

23568 votes

Category
longer_query
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Inkling

1,480.50 rating

Confidence interval: 1,467.97 – 1,493.02

2332 votes

Category
math
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Inkling

1,440.97 rating

Confidence interval: 1,433.45 – 1,448.48

7914 votes

Category
multi_turn
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Inkling

1,435.69 rating

Confidence interval: 1,430.93 – 1,440.45

29945 votes

Category
non_english
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Inkling

1,443.28 rating

Confidence interval: 1,439.20 – 1,447.36

50175 votes

Category
overall
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Inkling

1,451.17 rating

Confidence interval: 1,429.51 – 1,472.83

733 votes

Category
polish
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Inkling

1,433.57 rating

Confidence interval: 1,425.40 – 1,441.74

6314 votes

Category
russian
Evaluated configuration
Inkling
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Inkling

1,448.52 rating

Confidence interval: 1,432.63 – 1,464.41

1572 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