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 · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,346.04 rating
Confidence interval: 1,313.51 – 1,378.57
295 votes
Category
chinese
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,306.59 rating
Confidence interval: 1,282.30 – 1,330.87
519 votes
Category
coding
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,264.20 rating
Confidence interval: 1,240.62 – 1,287.77
568 votes
Category
creative_writing
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,305.07 rating
Confidence interval: 1,292.82 – 1,317.32
2255 votes
Category
english
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,216.94 rating
Confidence interval: 1,201.93 – 1,231.96
2472 votes
Category
exclude_ties
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,275.07 rating
Confidence interval: 1,239.27 – 1,310.87
228 votes
Category
expert
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,286.15 rating
Confidence interval: 1,267.53 – 1,304.76
889 votes
Category
hard_prompts
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating
Hunyuan Large (2025-02-10)
1,294.31 rating
Confidence interval: 1,271.91 – 1,316.71
601 votes
Category
hard_prompts_english
Evaluated configuration
Hunyuan Large (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating