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-large-vision
1,286.88 rating
Confidence interval: 1,254.51 – 1,319.25
327 votes
Category
chinese
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,308.12 rating
Confidence interval: 1,289.12 – 1,327.11
957 votes
Category
coding
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,247.42 rating
Confidence interval: 1,223.33 – 1,271.52
626 votes
Category
creative_writing
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,281.12 rating
Confidence interval: 1,268.74 – 1,293.49
2497 votes
Category
english
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,187.02 rating
Confidence interval: 1,174.18 – 1,199.86
3944 votes
Category
exclude_ties
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,251.67 rating
Confidence interval: 1,217.77 – 1,285.58
293 votes
Category
expert
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,256.49 rating
Confidence interval: 1,243.17 – 1,269.81
2148 votes
Category
hard_prompts
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
hunyuan-large-vision
1,270.72 rating
Confidence interval: 1,252.37 – 1,289.08
1058 votes
Category
hard_prompts_english
Evaluated configuration
hunyuan-large-vision
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating