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
Gemini 1.5 Flash (001)
1,234.16 rating
Confidence interval: 1,223.99 – 1,244.33
7043 votes
Category
chinese
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,235.37 rating
Confidence interval: 1,227.79 – 1,242.96
10680 votes
Category
coding
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,221.83 rating
Confidence interval: 1,213.47 – 1,230.20
9031 votes
Category
creative_writing
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,243.69 rating
Confidence interval: 1,238.34 – 1,249.03
33810 votes
Category
english
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,142.31 rating
Confidence interval: 1,135.61 – 1,149.02
40479 votes
Category
exclude_ties
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,199.08 rating
Confidence interval: 1,186.75 – 1,211.40
3194 votes
Category
expert
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,241.22 rating
Confidence interval: 1,217.01 – 1,265.44
919 votes
Category
french
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,216.42 rating
Confidence interval: 1,200.78 – 1,232.07
2169 votes
Category
german
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,219.50 rating
Confidence interval: 1,213.29 – 1,225.70
18228 votes
Category
hard_prompts
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Gemini 1.5 Flash (001)
1,224.57 rating
Confidence interval: 1,217.21 – 1,231.92
10974 votes
Category
hard_prompts_english
Evaluated configuration
Gemini 1.5 Flash (001)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating