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
MiniMax-M1
1,359.87 rating
Confidence interval: 1,347.55 – 1,372.19
2359 votes
Category
chinese
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
MiniMax-M1
1,358.37 rating
Confidence interval: 1,350.74 – 1,366.00
6396 votes
Category
coding
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
MiniMax-M1
1,297.35 rating
Confidence interval: 1,288.33 – 1,306.38
4502 votes
Category
creative_writing
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
MiniMax-M1
1,363.06 rating
Confidence interval: 1,357.49 – 1,368.62
14938 votes
Category
english
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
MiniMax-M1
1,298.06 rating
Confidence interval: 1,292.18 – 1,303.94
24072 votes
Category
exclude_ties
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
MiniMax-M1
1,316.56 rating
Confidence interval: 1,302.03 – 1,331.09
1631 votes
Category
expert
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
MiniMax-M1
1,370.60 rating
Confidence interval: 1,343.65 – 1,397.55
474 votes
Category
french
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
MiniMax-M1
1,349.80 rating
Confidence interval: 1,329.62 – 1,369.99
881 votes
Category
german
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
MiniMax-M1
1,339.19 rating
Confidence interval: 1,333.72 – 1,344.67
15593 votes
Category
hard_prompts
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
MiniMax-M1
1,353.35 rating
Confidence interval: 1,346.01 – 1,360.69
6992 votes
Category
hard_prompts_english
Evaluated configuration
MiniMax-M1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating