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-5.1
1,507.13 rating
Confidence interval: 1,493.74 – 1,520.52
2104 votes
Category
chinese
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
ernie-5.1
1,487.62 rating
Confidence interval: 1,480.72 – 1,494.51
10908 votes
Category
coding
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
ernie-5.1
1,440.57 rating
Confidence interval: 1,432.28 – 1,448.87
6454 votes
Category
creative_writing
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
ernie-5.1
1,477.30 rating
Confidence interval: 1,471.56 – 1,483.05
17981 votes
Category
english
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
ernie-5.1
1,471.72 rating
Confidence interval: 1,465.90 – 1,477.54
29999 votes
Category
exclude_ties
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
ernie-5.1
1,491.26 rating
Confidence interval: 1,481.03 – 1,501.50
3720 votes
Category
expert
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
ernie-5.1
1,486.07 rating
Confidence interval: 1,469.17 – 1,502.96
1507 votes
Category
french
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
ernie-5.1
1,470.83 rating
Confidence interval: 1,448.94 – 1,492.72
749 votes
Category
german
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
ernie-5.1
1,480.72 rating
Confidence interval: 1,475.45 – 1,486.00
25664 votes
Category
hard_prompts
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
ernie-5.1
1,484.56 rating
Confidence interval: 1,477.95 – 1,491.17
12424 votes
Category
hard_prompts_english
Evaluated configuration
ernie-5.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating