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 1412.6 Inkling Small · 95% interval 1408.0–1417.3 · 32,304 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 Small

1,463.14 rating

Confidence interval: 1,451.03 – 1,475.25

2589 votes

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

Inkling Small

1,451.51 rating

Confidence interval: 1,444.41 – 1,458.61

8848 votes

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

Inkling Small

1,331.20 rating

Confidence interval: 1,322.88 – 1,339.51

6963 votes

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

Inkling Small

1,421.19 rating

Confidence interval: 1,415.05 – 1,427.34

13225 votes

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

Inkling Small

1,396.81 rating

Confidence interval: 1,390.66 – 1,402.97

23772 votes

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

Inkling Small

1,441.85 rating

Confidence interval: 1,431.80 – 1,451.91

3781 votes

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

Inkling Small

1,432.68 rating

Confidence interval: 1,412.94 – 1,452.43

1030 votes

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

Inkling Small

1,406.65 rating

Confidence interval: 1,380.72 – 1,432.59

540 votes

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

Inkling Small

1,422.51 rating

Confidence interval: 1,417.12 – 1,427.91

21129 votes

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

Inkling Small

1,428.62 rating

Confidence interval: 1,421.42 – 1,435.82

8663 votes

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

Inkling Small

1,412.61 rating

Confidence interval: 1,404.31 – 1,420.91

6001 votes

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 · 2026-10-15 · rating

Inkling Small

1,350.93 rating

Confidence interval: 1,343.36 – 1,358.49

8419 votes

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

Inkling Small

1,415.78 rating

Confidence interval: 1,403.98 – 1,427.57

2801 votes

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

Inkling Small

1,427.03 rating

Confidence interval: 1,418.42 – 1,435.63

5384 votes

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

Inkling Small

1,440.96 rating

Confidence interval: 1,426.48 – 1,455.43

1748 votes

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

Inkling Small

1,411.40 rating

Confidence interval: 1,398.50 – 1,424.29

2332 votes

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

Inkling Small

1,447.15 rating

Confidence interval: 1,440.91 – 1,453.39

12584 votes

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

Inkling Small

1,355.28 rating

Confidence interval: 1,347.93 – 1,362.63

9076 votes

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

Inkling Small

1,398.74 rating

Confidence interval: 1,392.23 – 1,405.26

11768 votes

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

Inkling Small

1,401.14 rating

Confidence interval: 1,373.27 – 1,429.00

528 votes

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

Inkling Small

1,364.29 rating

Confidence interval: 1,339.19 – 1,389.39

583 votes

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

Inkling Small

1,400.67 rating

Confidence interval: 1,394.52 – 1,406.82

15204 votes

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

Inkling Small

1,457.47 rating

Confidence interval: 1,441.89 – 1,473.05

1455 votes

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

Inkling Small

1,414.22 rating

Confidence interval: 1,405.15 – 1,423.28

4945 votes

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

Inkling Small

1,399.59 rating

Confidence interval: 1,394.11 – 1,405.07

19075 votes

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

Inkling Small

1,412.62 rating

Confidence interval: 1,407.98 – 1,417.27

32304 votes

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

Inkling Small

1,426.06 rating

Confidence interval: 1,398.14 – 1,453.98

459 votes

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

Inkling Small

1,391.36 rating

Confidence interval: 1,381.33 – 1,401.39

3866 votes

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

Inkling Small

1,421.51 rating

Confidence interval: 1,401.97 – 1,441.06

966 votes

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