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
step-1o-turbo-202506
1,380.15 rating
Confidence interval: 1,354.97 – 1,405.34
545 votes
Category
chinese
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,338.91 rating
Confidence interval: 1,324.10 – 1,353.73
1494 votes
Category
coding
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,306.80 rating
Confidence interval: 1,287.92 – 1,325.68
991 votes
Category
creative_writing
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,352.71 rating
Confidence interval: 1,343.06 – 1,362.37
3993 votes
Category
english
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,288.29 rating
Confidence interval: 1,278.81 – 1,297.77
6353 votes
Category
exclude_ties
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,307.59 rating
Confidence interval: 1,281.09 – 1,334.08
484 votes
Category
expert
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,315.38 rating
Confidence interval: 1,283.81 – 1,346.95
341 votes
Category
german
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,335.00 rating
Confidence interval: 1,325.16 – 1,344.85
3693 votes
Category
hard_prompts
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
step-1o-turbo-202506
1,354.23 rating
Confidence interval: 1,340.21 – 1,368.25
1704 votes
Category
hard_prompts_english
Evaluated configuration
step-1o-turbo-202506
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating