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
ernie-5.0-0110
1,492.32 rating
Confidence interval: 1,480.32 – 1,504.33
2540 votes
Category
chinese
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,454.65 rating
Confidence interval: 1,448.10 – 1,461.20
8968 votes
Category
coding
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,425.84 rating
Confidence interval: 1,417.72 – 1,433.95
5765 votes
Category
creative_writing
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,448.46 rating
Confidence interval: 1,443.12 – 1,453.80
15134 votes
Category
english
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,443.28 rating
Confidence interval: 1,437.99 – 1,448.58
26021 votes
Category
exclude_ties
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,426.77 rating
Confidence interval: 1,415.94 – 1,437.61
2955 votes
Category
expert
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,458.83 rating
Confidence interval: 1,440.14 – 1,477.52
1094 votes
Category
french
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,435.29 rating
Confidence interval: 1,412.31 – 1,458.27
664 votes
Category
german
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,445.31 rating
Confidence interval: 1,440.58 – 1,450.05
21826 votes
Category
hard_prompts
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
ernie-5.0-0110
1,447.86 rating
Confidence interval: 1,441.32 – 1,454.40
9162 votes
Category
hard_prompts_english
Evaluated configuration
ernie-5.0-0110
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating