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 3 Pro
1,523.17 rating
Confidence interval: 1,512.81 – 1,533.54
3456 votes
Category
chinese
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,481.23 rating
Confidence interval: 1,474.34 – 1,488.12
8805 votes
Category
coding
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,482.09 rating
Confidence interval: 1,474.03 – 1,490.14
6544 votes
Category
creative_writing
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,477.66 rating
Confidence interval: 1,472.27 – 1,483.05
16953 votes
Category
english
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,490.99 rating
Confidence interval: 1,485.67 – 1,496.31
30188 votes
Category
exclude_ties
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,475.34 rating
Confidence interval: 1,464.21 – 1,486.48
2828 votes
Category
expert
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,492.75 rating
Confidence interval: 1,473.20 – 1,512.31
968 votes
Category
french
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,515.67 rating
Confidence interval: 1,493.78 – 1,537.55
812 votes
Category
german
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,480.26 rating
Confidence interval: 1,475.42 – 1,485.11
23177 votes
Category
hard_prompts
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Gemini 3 Pro
1,474.71 rating
Confidence interval: 1,467.95 – 1,481.47
9163 votes
Category
hard_prompts_english
Evaluated configuration
Gemini 3 Pro
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating