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
Yi 34B Chat
1,175.54 rating
Confidence interval: 1,157.43 – 1,193.64
1219 votes
Category
chinese
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Yi 34B Chat
1,111.48 rating
Confidence interval: 1,098.53 – 1,124.42
2345 votes
Category
coding
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Yi 34B Chat
1,107.74 rating
Confidence interval: 1,094.07 – 1,121.40
2379 votes
Category
creative_writing
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Yi 34B Chat
1,159.09 rating
Confidence interval: 1,151.20 – 1,166.98
10572 votes
Category
english
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Yi 34B Chat
976.19 rating
Confidence interval: 966.26 – 986.12
10427 votes
Category
exclude_ties
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Yi 34B Chat
1,061.13 rating
Confidence interval: 1,036.30 – 1,085.97
559 votes
Category
expert
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Yi 34B Chat
1,081.73 rating
Confidence interval: 1,040.49 – 1,122.96
234 votes
Category
french
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Yi 34B Chat
1,042.04 rating
Confidence interval: 1,009.89 – 1,074.20
381 votes
Category
german
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Yi 34B Chat
1,103.43 rating
Confidence interval: 1,092.93 – 1,113.92
3838 votes
Category
hard_prompts
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Yi 34B Chat
1,120.06 rating
Confidence interval: 1,108.10 – 1,132.02
2844 votes
Category
hard_prompts_english
Evaluated configuration
Yi 34B Chat
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating