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-7b-beta
959.96 rating
Confidence interval: 929.57 – 990.35
373 votes
Category
chinese
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,044.42 rating
Confidence interval: 1,026.36 – 1,062.47
1250 votes
Category
coding
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,102.15 rating
Confidence interval: 1,086.25 – 1,118.05
1993 votes
Category
creative_writing
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,107.31 rating
Confidence interval: 1,097.76 – 1,116.85
8764 votes
Category
english
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
zephyr-7b-beta
888.27 rating
Confidence interval: 875.99 – 900.55
7522 votes
Category
exclude_ties
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,005.76 rating
Confidence interval: 968.28 – 1,043.23
201 votes
Category
expert
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,030.92 rating
Confidence interval: 981.90 – 1,079.93
153 votes
Category
french
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
zephyr-7b-beta
989.01 rating
Confidence interval: 941.21 – 1,036.81
152 votes
Category
german
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,026.47 rating
Confidence interval: 1,012.27 – 1,040.67
2220 votes
Category
hard_prompts
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
zephyr-7b-beta
1,047.54 rating
Confidence interval: 1,032.20 – 1,062.88
1847 votes
Category
hard_prompts_english
Evaluated configuration
zephyr-7b-beta
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating