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
Jamba 1.5 Large
1,202.97 rating
Confidence interval: 1,181.18 – 1,224.76
675 votes
Category
chinese
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,227.24 rating
Confidence interval: 1,212.85 – 1,241.62
1440 votes
Category
coding
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,211.43 rating
Confidence interval: 1,195.55 – 1,227.31
1379 votes
Category
creative_writing
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,266.65 rating
Confidence interval: 1,257.47 – 1,275.82
4915 votes
Category
english
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,139.31 rating
Confidence interval: 1,128.10 – 1,150.53
5535 votes
Category
exclude_ties
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,217.42 rating
Confidence interval: 1,188.53 – 1,246.32
331 votes
Category
expert
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,199.81 rating
Confidence interval: 1,163.04 – 1,236.59
234 votes
Category
german
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,217.53 rating
Confidence interval: 1,205.96 – 1,229.10
2372 votes
Category
hard_prompts
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Jamba 1.5 Large
1,231.06 rating
Confidence interval: 1,217.18 – 1,244.94
1528 votes
Category
hard_prompts_english
Evaluated configuration
Jamba 1.5 Large
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating