GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude 3.5 Sonnet (20241022)

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 (20241022) 1297.8 Claude 3.5 Sonnet (20241022) · 95% interval 1294.6–1301.0 · 87,759 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 (20241022)

1,271.78 rating

Confidence interval: 1,263.58 – 1,279.99

6922 votes

Category
chinese
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,342.21 rating

Confidence interval: 1,336.73 – 1,347.69

14906 votes

Category
coding
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,291.68 rating

Confidence interval: 1,285.41 – 1,297.94

11710 votes

Category
creative_writing
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,307.11 rating

Confidence interval: 1,303.18 – 1,311.03

45070 votes

Category
english
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,235.74 rating

Confidence interval: 1,231.45 – 1,240.03

61462 votes

Category
exclude_ties
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,264.39 rating

Confidence interval: 1,255.19 – 1,273.59

5041 votes

Category
expert
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,305.14 rating

Confidence interval: 1,283.90 – 1,326.38

848 votes

Category
french
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,297.42 rating

Confidence interval: 1,283.91 – 1,310.92

2025 votes

Category
german
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,304.76 rating

Confidence interval: 1,300.44 – 1,309.09

27140 votes

Category
hard_prompts
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,311.22 rating

Confidence interval: 1,305.82 – 1,316.63

15031 votes

Category
hard_prompts_english
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,254.81 rating

Confidence interval: 1,248.48 – 1,261.14

11264 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,278.80 rating

Confidence interval: 1,273.14 – 1,284.46

14255 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,277.37 rating

Confidence interval: 1,268.36 – 1,286.37

5495 votes

Category
industry_legal_and_government
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,269.71 rating

Confidence interval: 1,263.99 – 1,275.43

15553 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,306.83 rating

Confidence interval: 1,299.86 – 1,313.80

8596 votes

Category
industry_mathematical
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,256.68 rating

Confidence interval: 1,246.82 – 1,266.55

4534 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,315.77 rating

Confidence interval: 1,311.18 – 1,320.36

24996 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,313.58 rating

Confidence interval: 1,308.63 – 1,318.52

21813 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,296.96 rating

Confidence interval: 1,292.53 – 1,301.38

31236 votes

Category
instruction_following
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,234.09 rating

Confidence interval: 1,219.89 – 1,248.30

2040 votes

Category
japanese
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,197.77 rating

Confidence interval: 1,179.09 – 1,216.46

1273 votes

Category
korean
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,310.91 rating

Confidence interval: 1,305.24 – 1,316.58

13766 votes

Category
longer_query
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,306.60 rating

Confidence interval: 1,299.97 – 1,313.24

10011 votes

Category
math
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,325.66 rating

Confidence interval: 1,319.98 – 1,331.33

15894 votes

Category
multi_turn
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,282.92 rating

Confidence interval: 1,279.06 – 1,286.78

42681 votes

Category
non_english
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,297.77 rating

Confidence interval: 1,294.58 – 1,300.96

87759 votes

Category
overall
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,287.82 rating

Confidence interval: 1,274.24 – 1,301.41

2217 votes

Category
polish
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,305.31 rating

Confidence interval: 1,298.58 – 1,312.04

10310 votes

Category
russian
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Claude 3.5 Sonnet (20241022)

1,285.56 rating

Confidence interval: 1,266.15 – 1,304.97

967 votes

Category
spanish
Evaluated configuration
Claude 3.5 Sonnet (20241022)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude 3.5 Sonnet (20241022)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary