GeekRadar / The comparison desk

COMPARE.

AI models

thinky

Inkling-Small

Model evaluation

Capability & preference

Human preference · Arena

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

Inkling-Small 1414.3 Inkling-Small · 95% interval 1409.8–1418.8 · 36,999 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

Inkling-Small

1,464.25 rating

Confidence interval: 1,452.81 – 1,475.70

2975 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Inkling-Small

1,450.94 rating

Confidence interval: 1,444.11 – 1,457.77

10049 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Inkling-Small

1,335.74 rating

Confidence interval: 1,327.79 – 1,343.69

7972 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Inkling-Small

1,420.13 rating

Confidence interval: 1,414.22 – 1,426.05

14988 votes

Oct 28, 2026

Category: english
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Inkling-Small

1,399.01 rating

Confidence interval: 1,393.09 – 1,404.94

27243 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Inkling-Small

1,440.55 rating

Confidence interval: 1,430.98 – 1,450.11

4292 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Inkling-Small

1,435.06 rating

Confidence interval: 1,416.89 – 1,453.23

1235 votes

Oct 28, 2026

Category: french
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Inkling-Small

1,403.54 rating

Confidence interval: 1,379.24 – 1,427.83

626 votes

Oct 28, 2026

Category: german
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Inkling-Small

1,424.17 rating

Confidence interval: 1,418.99 – 1,429.35

24140 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Inkling-Small

1,428.29 rating

Confidence interval: 1,421.38 – 1,435.20

9830 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Inkling-Small

1,413.55 rating

Confidence interval: 1,405.60 – 1,421.50

6813 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Inkling-Small

1,352.71 rating

Confidence interval: 1,345.48 – 1,359.94

9634 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Inkling-Small

1,413.90 rating

Confidence interval: 1,402.69 – 1,425.11

3157 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Inkling-Small

1,427.46 rating

Confidence interval: 1,419.22 – 1,435.69

6110 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Inkling-Small

1,439.90 rating

Confidence interval: 1,426.37 – 1,453.43

2039 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Inkling-Small

1,414.28 rating

Confidence interval: 1,402.01 – 1,426.55

2650 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Inkling-Small

1,448.21 rating

Confidence interval: 1,442.21 – 1,454.22

14266 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Inkling-Small

1,358.21 rating

Confidence interval: 1,351.17 – 1,365.26

10395 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Inkling-Small

1,400.94 rating

Confidence interval: 1,394.70 – 1,407.19

13454 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Inkling-Small

1,393.73 rating

Confidence interval: 1,368.05 – 1,419.40

626 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Inkling-Small

1,373.80 rating

Confidence interval: 1,350.07 – 1,397.54

658 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Inkling-Small

1,403.88 rating

Confidence interval: 1,397.96 – 1,409.80

17285 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Inkling-Small

1,458.32 rating

Confidence interval: 1,443.91 – 1,472.74

1727 votes

Oct 28, 2026

Category: math
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Inkling-Small

1,415.94 rating

Confidence interval: 1,407.34 – 1,424.54

5706 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Inkling-Small

1,402.56 rating

Confidence interval: 1,397.30 – 1,407.83

22004 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Inkling-Small

1,414.32 rating

Confidence interval: 1,409.82 – 1,418.82

36999 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Inkling-Small

1,427.90 rating

Confidence interval: 1,402.03 – 1,453.78

535 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Inkling-Small

1,396.09 rating

Confidence interval: 1,386.68 – 1,405.51

4500 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Inkling-Small

1,427.15 rating

Confidence interval: 1,408.96 – 1,445.34

1134 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Inkling-Small
Evaluation type: human preference

Run it locally

Inference · memory estimate

Inkling-Small

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Apache 2.0