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
mimo-v2-flash (thinking)
1,428.61 rating
Confidence interval: 1,408.65 – 1,448.57
792 votes
Category
chinese
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,418.53 rating
Confidence interval: 1,406.87 – 1,430.18
2491 votes
Category
coding
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,348.04 rating
Confidence interval: 1,334.11 – 1,361.96
1756 votes
Category
creative_writing
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,411.74 rating
Confidence interval: 1,402.76 – 1,420.71
4365 votes
Category
english
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,370.43 rating
Confidence interval: 1,361.84 – 1,379.02
7756 votes
Category
exclude_ties
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,400.98 rating
Confidence interval: 1,380.68 – 1,421.28
769 votes
Category
expert
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,428.84 rating
Confidence interval: 1,398.22 – 1,459.45
349 votes
Category
french
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,394.99 rating
Confidence interval: 1,358.29 – 1,431.69
261 votes
Category
german
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,403.55 rating
Confidence interval: 1,395.83 – 1,411.28
6189 votes
Category
hard_prompts
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
mimo-v2-flash (thinking)
1,417.16 rating
Confidence interval: 1,405.26 – 1,429.05
2354 votes
Category
hard_prompts_english
Evaluated configuration
mimo-v2-flash (thinking)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating