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
hunyuan-turbo-0110
1,357.64 rating
Confidence interval: 1,318.59 – 1,396.69
208 votes
Category
chinese
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,319.23 rating
Confidence interval: 1,289.92 – 1,348.53
299 votes
Category
coding
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,268.86 rating
Confidence interval: 1,244.06 – 1,293.66
451 votes
Category
creative_writing
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,328.71 rating
Confidence interval: 1,314.35 – 1,343.08
1319 votes
Category
english
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,248.49 rating
Confidence interval: 1,229.54 – 1,267.44
1358 votes
Category
exclude_ties
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,307.99 rating
Confidence interval: 1,284.91 – 1,331.07
496 votes
Category
hard_prompts
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
hunyuan-turbo-0110
1,326.68 rating
Confidence interval: 1,299.39 – 1,353.97
343 votes
Category
hard_prompts_english
Evaluated configuration
hunyuan-turbo-0110
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating