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
dola-seed-2.0-pro
1,489.26 rating
Confidence interval: 1,480.47 – 1,498.05
5277 votes
Category
chinese
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,471.92 rating
Confidence interval: 1,466.63 – 1,477.21
22061 votes
Category
coding
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,406.15 rating
Confidence interval: 1,399.94 – 1,412.37
13208 votes
Category
creative_writing
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,449.30 rating
Confidence interval: 1,444.80 – 1,453.79
35253 votes
Category
english
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,446.62 rating
Confidence interval: 1,442.18 – 1,451.07
60065 votes
Category
exclude_ties
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,439.51 rating
Confidence interval: 1,432.00 – 1,447.02
7790 votes
Category
expert
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,471.25 rating
Confidence interval: 1,457.85 – 1,484.66
2580 votes
Category
french
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,442.24 rating
Confidence interval: 1,424.71 – 1,459.77
1319 votes
Category
german
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,453.26 rating
Confidence interval: 1,449.19 – 1,457.33
50968 votes
Category
hard_prompts
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
dola-seed-2.0-pro
1,449.76 rating
Confidence interval: 1,444.56 – 1,454.96
23405 votes
Category
hard_prompts_english
Evaluated configuration
dola-seed-2.0-pro
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating