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-M2.7
1,440.65 rating
Confidence interval: 1,432.21 – 1,449.09
5879 votes
Category
chinese
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,453.63 rating
Confidence interval: 1,448.71 – 1,458.55
25186 votes
Category
coding
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,353.82 rating
Confidence interval: 1,347.87 – 1,359.77
15328 votes
Category
creative_writing
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,425.68 rating
Confidence interval: 1,421.37 – 1,429.99
36637 votes
Category
english
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,387.72 rating
Confidence interval: 1,383.45 – 1,392.00
67257 votes
Category
exclude_ties
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,443.15 rating
Confidence interval: 1,436.07 – 1,450.22
8902 votes
Category
expert
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,424.78 rating
Confidence interval: 1,412.64 – 1,436.92
3395 votes
Category
french
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,397.62 rating
Confidence interval: 1,381.18 – 1,414.05
1529 votes
Category
german
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,422.32 rating
Confidence interval: 1,418.46 – 1,426.18
57903 votes
Category
hard_prompts
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
MiniMax-M2.7
1,440.54 rating
Confidence interval: 1,435.58 – 1,445.51
24694 votes
Category
hard_prompts_english
Evaluated configuration
MiniMax-M2.7
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,360.53 rating
Confidence interval: 1,355.01 – 1,366.05
18736 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,403.39 rating
Confidence interval: 1,395.27 – 1,411.51
6534 votes
Category
industry_legal_and_government
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,416.68 rating
Confidence interval: 1,410.72 – 1,422.65
13637 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,437.75 rating
Confidence interval: 1,428.22 – 1,447.28
4519 votes
Category
industry_mathematical
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,409.14 rating
Confidence interval: 1,400.57 – 1,417.71
5829 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,445.95 rating
Confidence interval: 1,441.50 – 1,450.40
34214 votes
Category
industry_software_and_it_services
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,376.04 rating
Confidence interval: 1,370.77 – 1,381.30
20686 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,405.03 rating
Confidence interval: 1,400.30 – 1,409.75
28460 votes
Category
instruction_following
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,261.30 rating
Confidence interval: 1,239.88 – 1,282.72
1111 votes
Category
japanese
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,313.68 rating
Confidence interval: 1,296.86 – 1,330.49
1535 votes
Category
korean
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,418.76 rating
Confidence interval: 1,414.20 – 1,423.33
36152 votes
Category
longer_query
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,420.27 rating
Confidence interval: 1,410.67 – 1,429.86
4268 votes
Category
math
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,411.97 rating
Confidence interval: 1,406.00 – 1,417.94
14532 votes
Category
multi_turn
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,382.34 rating
Confidence interval: 1,378.38 – 1,386.31
49817 votes
Category
non_english
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,404.83 rating
Confidence interval: 1,401.51 – 1,408.16
84977 votes
Category
overall
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,388.39 rating
Confidence interval: 1,373.43 – 1,403.35
1648 votes
Category
polish
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,382.76 rating
Confidence interval: 1,376.10 – 1,389.42
10254 votes
Category
russian
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
MiniMax-M2.7
1,402.03 rating
Confidence interval: 1,389.37 – 1,414.70
2710 votes
Category
spanish
Evaluated configuration
minimax-m2.7
Evaluation type
human preference
Run it locally
Inference · memory estimate
MiniMax-M2.7
Not enough verified architecture information for a reliable VRAM estimate.
API cost
USD / month
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.