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 Mini
1,135.54 rating
Confidence interval: 1,114.13 – 1,156.95
711 votes
Category
chinese
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,178.00 rating
Confidence interval: 1,162.85 – 1,193.16
1352 votes
Category
coding
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,164.06 rating
Confidence interval: 1,148.53 – 1,179.59
1399 votes
Category
creative_writing
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,223.97 rating
Confidence interval: 1,215.00 – 1,232.94
5087 votes
Category
english
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,056.77 rating
Confidence interval: 1,045.05 – 1,068.50
5612 votes
Category
exclude_ties
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,135.38 rating
Confidence interval: 1,104.76 – 1,165.99
332 votes
Category
expert
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,161.95 rating
Confidence interval: 1,123.81 – 1,200.10
248 votes
Category
german
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,166.66 rating
Confidence interval: 1,154.91 – 1,178.41
2350 votes
Category
hard_prompts
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Jamba 1.5 Mini
1,181.78 rating
Confidence interval: 1,167.59 – 1,195.98
1545 votes
Category
hard_prompts_english
Evaluated configuration
Jamba 1.5 Mini
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating