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-preview-1022
1,511.89 rating
Confidence interval: 1,482.35 – 1,541.43
390 votes
Category
chinese
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,412.39 rating
Confidence interval: 1,393.92 – 1,430.86
931 votes
Category
coding
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,415.97 rating
Confidence interval: 1,394.23 – 1,437.71
740 votes
Category
creative_writing
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,429.15 rating
Confidence interval: 1,417.12 – 1,441.17
2211 votes
Category
english
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,423.76 rating
Confidence interval: 1,411.27 – 1,436.25
3272 votes
Category
exclude_ties
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,418.77 rating
Confidence interval: 1,385.62 – 1,451.92
288 votes
Category
expert
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,420.61 rating
Confidence interval: 1,409.39 – 1,431.83
2589 votes
Category
hard_prompts
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
ernie-5.0-preview-1022
1,413.31 rating
Confidence interval: 1,397.43 – 1,429.20
1234 votes
Category
hard_prompts_english
Evaluated configuration
ernie-5.0-preview-1022
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating