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
Athene V2 Chat
1,301.76 rating
Confidence interval: 1,287.85 – 1,315.67
1781 votes
Category
chinese
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Athene V2 Chat
1,311.88 rating
Confidence interval: 1,302.82 – 1,320.94
4019 votes
Category
coding
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Athene V2 Chat
1,234.03 rating
Confidence interval: 1,224.30 – 1,243.77
3713 votes
Category
creative_writing
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Athene V2 Chat
1,306.83 rating
Confidence interval: 1,301.13 – 1,312.54
13676 votes
Category
english
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Athene V2 Chat
1,223.56 rating
Confidence interval: 1,216.53 – 1,230.58
15433 votes
Category
exclude_ties
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Athene V2 Chat
1,268.00 rating
Confidence interval: 1,253.04 – 1,282.97
1469 votes
Category
expert
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Athene V2 Chat
1,333.24 rating
Confidence interval: 1,296.06 – 1,370.42
228 votes
Category
french
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Athene V2 Chat
1,260.68 rating
Confidence interval: 1,238.09 – 1,283.27
626 votes
Category
german
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Athene V2 Chat
1,292.38 rating
Confidence interval: 1,285.05 – 1,299.72
6517 votes
Category
hard_prompts
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Athene V2 Chat
1,303.90 rating
Confidence interval: 1,294.85 – 1,312.95
4039 votes
Category
hard_prompts_english
Evaluated configuration
Athene V2 Chat
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating