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 / codinghuman preference · 2026-10-28 · rating
Guanaco 33B
995.24 rating
Confidence interval: 960.73 – 1,029.75
263 votes
Category
coding
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Guanaco 33B
1,079.69 rating
Confidence interval: 1,052.50 – 1,106.88
515 votes
Category
creative_writing
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Guanaco 33B
1,085.37 rating
Confidence interval: 1,071.96 – 1,098.78
2352 votes
Category
english
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Guanaco 33B
871.93 rating
Confidence interval: 854.31 – 889.55
2032 votes
Category
exclude_ties
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Guanaco 33B
1,004.92 rating
Confidence interval: 980.39 – 1,029.44
517 votes
Category
hard_prompts
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Guanaco 33B
1,020.24 rating
Confidence interval: 992.75 – 1,047.74
434 votes
Category
hard_prompts_english
Evaluated configuration
Guanaco 33B
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating