GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude 3.5 Sonnet (20240620)

Model evaluation

Capability & preference

Human preference · Arena

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

Claude 3.5 Sonnet (20240620) 1280.9 Claude 3.5 Sonnet (20240620) · 95% interval 1277.5–1284.3 · 82,419 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

Claude 3.5 Sonnet (20240620)

1,264.78 rating

Confidence interval: 1,255.45 – 1,274.10

8100 votes

Category
chinese
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,306.25 rating

Confidence interval: 1,299.26 – 1,313.24

13607 votes

Category
coding
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,237.78 rating

Confidence interval: 1,230.15 – 1,245.41

12430 votes

Category
creative_writing
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,287.33 rating

Confidence interval: 1,282.84 – 1,291.82

44433 votes

Category
english
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,205.73 rating

Confidence interval: 1,200.55 – 1,210.91

55109 votes

Category
exclude_ties
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,246.71 rating

Confidence interval: 1,235.65 – 1,257.77

4314 votes

Category
expert
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,293.70 rating

Confidence interval: 1,270.19 – 1,317.22

936 votes

Category
french
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,270.76 rating

Confidence interval: 1,255.92 – 1,285.61

2499 votes

Category
german
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,275.17 rating

Confidence interval: 1,269.60 – 1,280.73

23249 votes

Category
hard_prompts
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,282.30 rating

Confidence interval: 1,275.49 – 1,289.11

14269 votes

Category
hard_prompts_english
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,234.68 rating

Confidence interval: 1,226.50 – 1,242.86

9702 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,238.53 rating

Confidence interval: 1,231.28 – 1,245.78

13185 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,265.85 rating

Confidence interval: 1,254.92 – 1,276.78

4818 votes

Category
industry_legal_and_government
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,269.82 rating

Confidence interval: 1,262.63 – 1,277.01

13749 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,293.66 rating

Confidence interval: 1,285.85 – 1,301.47

10038 votes

Category
industry_mathematical
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,244.63 rating

Confidence interval: 1,233.20 – 1,256.06

4460 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,288.22 rating

Confidence interval: 1,282.36 – 1,294.09

22198 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,279.96 rating

Confidence interval: 1,273.86 – 1,286.05

21916 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,269.45 rating

Confidence interval: 1,264.36 – 1,274.54

32074 votes

Category
instruction_following
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,230.87 rating

Confidence interval: 1,214.59 – 1,247.15

2127 votes

Category
japanese
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,200.53 rating

Confidence interval: 1,180.98 – 1,220.07

1715 votes

Category
korean
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,274.69 rating

Confidence interval: 1,267.01 – 1,282.37

10574 votes

Category
longer_query
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,303.33 rating

Confidence interval: 1,295.87 – 1,310.79

11359 votes

Category
math
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,299.12 rating

Confidence interval: 1,291.97 – 1,306.26

14950 votes

Category
multi_turn
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,269.86 rating

Confidence interval: 1,265.12 – 1,274.61

37986 votes

Category
non_english
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,280.88 rating

Confidence interval: 1,277.46 – 1,284.30

82419 votes

Category
overall
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,328.43 rating

Confidence interval: 1,260.46 – 1,396.41

97 votes

Category
polish
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,282.41 rating

Confidence interval: 1,274.39 – 1,290.43

9966 votes

Category
russian
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20240620)

1,289.55 rating

Confidence interval: 1,267.22 – 1,311.89

1123 votes

Category
spanish
Evaluated configuration
Claude 3.5 Sonnet (20240620)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude 3.5 Sonnet (20240620)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary