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
Snowflake Arctic Instruct
1,067.02 rating
Confidence interval: 1,053.31 – 1,080.73
3128 votes
Category
chinese
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,089.13 rating
Confidence interval: 1,077.96 – 1,100.29
5734 votes
Category
coding
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,080.62 rating
Confidence interval: 1,068.64 – 1,092.60
4777 votes
Category
creative_writing
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,121.59 rating
Confidence interval: 1,114.13 – 1,129.05
20419 votes
Category
english
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
927.17 rating
Confidence interval: 917.65 – 936.68
21547 votes
Category
exclude_ties
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,028.07 rating
Confidence interval: 1,010.93 – 1,045.21
1722 votes
Category
expert
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,132.11 rating
Confidence interval: 1,101.64 – 1,162.58
527 votes
Category
french
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,073.61 rating
Confidence interval: 1,051.04 – 1,096.18
947 votes
Category
german
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,071.38 rating
Confidence interval: 1,062.30 – 1,080.46
9592 votes
Category
hard_prompts
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Snowflake Arctic Instruct
1,088.03 rating
Confidence interval: 1,077.27 – 1,098.78
6488 votes
Category
hard_prompts_english
Evaluated configuration
Snowflake Arctic Instruct
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating