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
zephyr-orpo-141b-A35b-v0.1
1,081.98 rating
Confidence interval: 1,058.83 – 1,105.13
657 votes
Category
chinese
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,129.03 rating
Confidence interval: 1,108.63 – 1,149.43
831 votes
Category
coding
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,113.01 rating
Confidence interval: 1,089.95 – 1,136.06
635 votes
Category
creative_writing
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,174.36 rating
Confidence interval: 1,161.21 – 1,187.50
2702 votes
Category
english
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
998.29 rating
Confidence interval: 982.70 – 1,013.89
3178 votes
Category
exclude_ties
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,061.62 rating
Confidence interval: 1,021.81 – 1,101.43
219 votes
Category
expert
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,115.60 rating
Confidence interval: 1,099.02 – 1,132.17
1240 votes
Category
hard_prompts
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
zephyr-orpo-141b-A35b-v0.1
1,132.89 rating
Confidence interval: 1,112.68 – 1,153.10
820 votes
Category
hard_prompts_english
Evaluated configuration
zephyr-orpo-141b-A35b-v0.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating