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 · 2026-10-15 · rating
gemini-1.5-flash-002
1,294.78 rating
Confidence interval: 1,283.34 – 1,306.22
2980 votes
Category
chinese
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,261.34 rating
Confidence interval: 1,253.35 – 1,269.32
5892 votes
Category
coding
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,285.27 rating
Confidence interval: 1,276.38 – 1,294.15
5017 votes
Category
creative_writing
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,288.54 rating
Confidence interval: 1,283.12 – 1,293.95
18364 votes
Category
english
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,215.20 rating
Confidence interval: 1,208.72 – 1,221.67
22474 votes
Category
exclude_ties
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,232.87 rating
Confidence interval: 1,219.80 – 1,245.93
2116 votes
Category
expert
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,258.25 rating
Confidence interval: 1,223.81 – 1,292.69
295 votes
Category
french
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,261.58 rating
Confidence interval: 1,240.11 – 1,283.04
739 votes
Category
german
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,257.09 rating
Confidence interval: 1,250.45 – 1,263.74
9262 votes
Category
hard_prompts
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
gemini-1.5-flash-002
1,264.60 rating
Confidence interval: 1,256.45 – 1,272.76
5484 votes
Category
hard_prompts_english
Evaluated configuration
gemini-1.5-flash-002
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating