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
qwen-max-0919
1,253.97 rating
Confidence interval: 1,238.36 – 1,269.59
1421 votes
Category
chinese
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
qwen-max-0919
1,287.89 rating
Confidence interval: 1,276.78 – 1,299.01
2756 votes
Category
coding
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
qwen-max-0919
1,247.95 rating
Confidence interval: 1,235.96 – 1,259.95
2358 votes
Category
creative_writing
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
qwen-max-0919
1,292.49 rating
Confidence interval: 1,285.20 – 1,299.77
8347 votes
Category
english
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
qwen-max-0919
1,205.68 rating
Confidence interval: 1,197.12 – 1,214.24
10342 votes
Category
exclude_ties
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
qwen-max-0919
1,247.79 rating
Confidence interval: 1,229.80 – 1,265.78
1011 votes
Category
expert
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
qwen-max-0919
1,330.06 rating
Confidence interval: 1,288.88 – 1,371.25
183 votes
Category
french
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
qwen-max-0919
1,253.89 rating
Confidence interval: 1,227.70 – 1,280.09
438 votes
Category
german
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
qwen-max-0919
1,269.29 rating
Confidence interval: 1,260.08 – 1,278.50
4447 votes
Category
hard_prompts
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
qwen-max-0919
1,280.41 rating
Confidence interval: 1,269.13 – 1,291.69
2531 votes
Category
hard_prompts_english
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating