GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude 3.7 Sonnet (Thinking 32K, 20250219)

Model evaluation

Capability & preference

Human preference · Arena

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

Claude 3.7 Sonnet (Thinking 32K, 20250219) 1314.4 Claude 3.7 Sonnet (Thinking 32K, 20250219) · 95% interval 1310.1–1318.6 · 38,126 votes · 2026-11-09

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 · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,299.01 rating

Confidence interval: 1,286.26 – 1,311.76

2311 votes

Category
chinese
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,360.56 rating

Confidence interval: 1,352.63 – 1,368.49

6128 votes

Category
coding
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,331.89 rating

Confidence interval: 1,323.26 – 1,340.53

5145 votes

Category
creative_writing
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,326.33 rating

Confidence interval: 1,321.02 – 1,331.65

18892 votes

Category
english
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,260.77 rating

Confidence interval: 1,255.16 – 1,266.38

28155 votes

Category
exclude_ties
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,320.33 rating

Confidence interval: 1,306.42 – 1,334.24

1887 votes

Category
expert
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,288.89 rating

Confidence interval: 1,260.87 – 1,316.91

512 votes

Category
french
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,300.31 rating

Confidence interval: 1,280.94 – 1,319.67

1021 votes

Category
german
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,333.15 rating

Confidence interval: 1,327.23 – 1,339.08

13708 votes

Category
hard_prompts
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,339.84 rating

Confidence interval: 1,332.25 – 1,347.43

6975 votes

Category
hard_prompts_english
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,268.96 rating

Confidence interval: 1,260.39 – 1,277.54

5592 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,313.46 rating

Confidence interval: 1,305.75 – 1,321.18

6537 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,301.54 rating

Confidence interval: 1,289.13 – 1,313.94

2473 votes

Category
industry_legal_and_government
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,298.49 rating

Confidence interval: 1,290.43 – 1,306.54

6701 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,338.78 rating

Confidence interval: 1,327.26 – 1,350.30

2541 votes

Category
industry_mathematical
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,288.07 rating

Confidence interval: 1,274.62 – 1,301.51

2241 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,323.89 rating

Confidence interval: 1,317.49 – 1,330.29

11400 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,337.73 rating

Confidence interval: 1,330.87 – 1,344.59

8761 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,351.66 rating

Confidence interval: 1,345.23 – 1,358.09

10119 votes

Category
instruction_following
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,267.05 rating

Confidence interval: 1,247.34 – 1,286.76

1018 votes

Category
japanese
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,249.75 rating

Confidence interval: 1,226.42 – 1,273.09

766 votes

Category
korean
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,372.77 rating

Confidence interval: 1,364.89 – 1,380.66

6134 votes

Category
longer_query
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,336.23 rating

Confidence interval: 1,325.25 – 1,347.20

2783 votes

Category
math
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,337.36 rating

Confidence interval: 1,329.25 – 1,345.48

6137 votes

Category
multi_turn
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,296.06 rating

Confidence interval: 1,290.74 – 1,301.38

19222 votes

Category
non_english
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,314.36 rating

Confidence interval: 1,310.11 – 1,318.60

38126 votes

Category
overall
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,284.17 rating

Confidence interval: 1,270.25 – 1,298.09

2193 votes

Category
polish
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,310.93 rating

Confidence interval: 1,300.58 – 1,321.29

3354 votes

Category
russian
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-09 · rating

Claude 3.7 Sonnet (Thinking 32K, 20250219)

1,298.67 rating

Confidence interval: 1,273.76 – 1,323.58

611 votes

Category
spanish
Evaluated configuration
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude 3.7 Sonnet (Thinking 32K, 20250219)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary