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-pro-001
1,274.74 rating
Confidence interval: 1,264.86 – 1,284.63
8912 votes
Category
chinese
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,266.11 rating
Confidence interval: 1,258.66 – 1,273.56
12747 votes
Category
coding
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,272.33 rating
Confidence interval: 1,264.23 – 1,280.42
11797 votes
Category
creative_writing
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,279.20 rating
Confidence interval: 1,274.10 – 1,284.30
42538 votes
Category
english
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,195.04 rating
Confidence interval: 1,188.83 – 1,201.24
52502 votes
Category
exclude_ties
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,244.69 rating
Confidence interval: 1,232.69 – 1,256.69
3896 votes
Category
expert
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,272.09 rating
Confidence interval: 1,249.18 – 1,295.00
1076 votes
Category
french
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,249.14 rating
Confidence interval: 1,234.12 – 1,264.16
2677 votes
Category
german
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,254.73 rating
Confidence interval: 1,248.65 – 1,260.82
22512 votes
Category
hard_prompts
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
gemini-1.5-pro-001
1,258.65 rating
Confidence interval: 1,251.45 – 1,265.84
13552 votes
Category
hard_prompts_english
Evaluated configuration
gemini-1.5-pro-001
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating