GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

claude-3-sonnet-20240229

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-sonnet-20240229 1218.0 claude-3-sonnet-20240229 · 95% interval 1214.0–1222.0 · 109,284 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

claude-3-sonnet-20240229

1,188.60 rating

Confidence interval: 1,179.33 – 1,197.88

15648 votes

Category
chinese
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,222.54 rating

Confidence interval: 1,215.26 – 1,229.82

18888 votes

Category
coding
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,186.03 rating

Confidence interval: 1,177.81 – 1,194.25

15592 votes

Category
creative_writing
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,226.05 rating

Confidence interval: 1,221.16 – 1,230.94

60970 votes

Category
english
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,108.15 rating

Confidence interval: 1,102.35 – 1,113.96

73557 votes

Category
exclude_ties
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,172.29 rating

Confidence interval: 1,160.49 – 1,184.08

5614 votes

Category
expert
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,229.12 rating

Confidence interval: 1,208.13 – 1,250.11

1824 votes

Category
french
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,203.73 rating

Confidence interval: 1,188.57 – 1,218.89

3097 votes

Category
german
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,196.86 rating

Confidence interval: 1,190.96 – 1,202.77

30725 votes

Category
hard_prompts
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,202.30 rating

Confidence interval: 1,195.09 – 1,209.50

19193 votes

Category
hard_prompts_english
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,173.99 rating

Confidence interval: 1,165.05 – 1,182.93

11853 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,171.35 rating

Confidence interval: 1,163.52 – 1,179.17

15961 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,213.59 rating

Confidence interval: 1,201.75 – 1,225.43

6062 votes

Category
industry_legal_and_government
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,209.09 rating

Confidence interval: 1,201.46 – 1,216.72

19089 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,213.01 rating

Confidence interval: 1,204.61 – 1,221.41

12413 votes

Category
industry_mathematical
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,188.19 rating

Confidence interval: 1,176.11 – 1,200.28

5941 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,220.83 rating

Confidence interval: 1,214.70 – 1,226.97

31448 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,217.72 rating

Confidence interval: 1,211.13 – 1,224.30

27297 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,199.23 rating

Confidence interval: 1,193.63 – 1,204.83

38802 votes

Category
instruction_following
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,131.11 rating

Confidence interval: 1,112.89 – 1,149.32

1753 votes

Category
japanese
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,127.77 rating

Confidence interval: 1,108.33 – 1,147.21

2059 votes

Category
korean
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,210.79 rating

Confidence interval: 1,202.17 – 1,219.40

11870 votes

Category
longer_query
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,213.36 rating

Confidence interval: 1,205.31 – 1,221.40

13766 votes

Category
math
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,226.84 rating

Confidence interval: 1,218.92 – 1,234.77

17062 votes

Category
multi_turn
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,205.13 rating

Confidence interval: 1,199.91 – 1,210.34

48314 votes

Category
non_english
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,218.00 rating

Confidence interval: 1,214.05 – 1,221.95

109284 votes

Category
overall
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,259.39 rating

Confidence interval: 1,206.92 – 1,311.86

284 votes

Category
polish
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,226.57 rating

Confidence interval: 1,217.47 – 1,235.68

10794 votes

Category
russian
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

claude-3-sonnet-20240229

1,204.18 rating

Confidence interval: 1,182.22 – 1,226.14

1448 votes

Category
spanish
Evaluated configuration
claude-3-sonnet-20240229
Evaluation type
human preference

Run it locally

Inference · memory estimate

claude-3-sonnet-20240229

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary