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 · 2026-10-28 · rating
Muse Wonder (Max)
1,531.06 rating
Confidence interval: 1,508.29 – 1,553.84
647 votes
Category
chinese
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,518.44 rating
Confidence interval: 1,504.57 – 1,532.32
1902 votes
Category
coding
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,488.30 rating
Confidence interval: 1,473.13 – 1,503.46
1736 votes
Category
creative_writing
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,504.81 rating
Confidence interval: 1,493.59 – 1,516.03
3050 votes
Category
english
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,515.93 rating
Confidence interval: 1,505.80 – 1,526.05
5636 votes
Category
exclude_ties
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,505.63 rating
Confidence interval: 1,485.69 – 1,525.58
826 votes
Category
expert
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,506.63 rating
Confidence interval: 1,473.75 – 1,539.51
342 votes
Category
french
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,506.94 rating
Confidence interval: 1,497.88 – 1,516.00
4834 votes
Category
hard_prompts
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Muse Wonder (Max)
1,509.78 rating
Confidence interval: 1,495.85 – 1,523.71
1945 votes
Category
hard_prompts_english
Evaluated configuration
Muse Wonder (Max)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating