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
openchat-3.5-0106
1,083.72 rating
Confidence interval: 1,066.29 – 1,101.15
1525 votes
Category
chinese
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,112.72 rating
Confidence interval: 1,098.82 – 1,126.62
2005 votes
Category
coding
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,092.32 rating
Confidence interval: 1,077.47 – 1,107.17
1858 votes
Category
creative_writing
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,131.10 rating
Confidence interval: 1,122.35 – 1,139.86
8216 votes
Category
english
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
openchat-3.5-0106
943.86 rating
Confidence interval: 932.41 – 955.31
8130 votes
Category
exclude_ties
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,052.27 rating
Confidence interval: 1,029.35 – 1,075.18
611 votes
Category
expert
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,092.23 rating
Confidence interval: 1,048.92 – 1,135.54
211 votes
Category
french
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,059.86 rating
Confidence interval: 1,025.26 – 1,094.47
268 votes
Category
german
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,084.81 rating
Confidence interval: 1,073.76 – 1,095.86
3435 votes
Category
hard_prompts
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
openchat-3.5-0106
1,094.73 rating
Confidence interval: 1,082.39 – 1,107.07
2468 votes
Category
hard_prompts_english
Evaluated configuration
openchat-3.5-0106
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating