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-3-5-sonnet-20240620
1,264.69 rating
Confidence interval: 1,255.36 – 1,274.01
8100 votes
Category
chinese
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,306.33 rating
Confidence interval: 1,299.34 – 1,313.32
13607 votes
Category
coding
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,237.95 rating
Confidence interval: 1,230.32 – 1,245.58
12430 votes
Category
creative_writing
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,287.25 rating
Confidence interval: 1,282.77 – 1,291.74
44433 votes
Category
english
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,205.78 rating
Confidence interval: 1,200.61 – 1,210.96
55109 votes
Category
exclude_ties
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,246.69 rating
Confidence interval: 1,235.63 – 1,257.76
4314 votes
Category
expert
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,293.67 rating
Confidence interval: 1,270.13 – 1,317.21
936 votes
Category
french
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,270.80 rating
Confidence interval: 1,256.04 – 1,285.56
2499 votes
Category
german
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,275.25 rating
Confidence interval: 1,269.69 – 1,280.82
23249 votes
Category
hard_prompts
Evaluated configuration
claude-3-5-sonnet-20240620
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
claude-3-5-sonnet-20240620
1,282.25 rating
Confidence interval: 1,275.44 – 1,289.06
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 · 2026-10-15 · rating