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
gpt-4.1-nano-2025-04-14
1,270.06 rating
Confidence interval: 1,234.30 – 1,305.83
246 votes
Category
chinese
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,305.48 rating
Confidence interval: 1,286.22 – 1,324.73
807 votes
Category
coding
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,259.96 rating
Confidence interval: 1,241.76 – 1,278.17
1005 votes
Category
creative_writing
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,303.18 rating
Confidence interval: 1,293.38 – 1,312.97
3528 votes
Category
english
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,210.28 rating
Confidence interval: 1,198.25 – 1,222.31
3981 votes
Category
exclude_ties
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,271.32 rating
Confidence interval: 1,241.19 – 1,301.45
328 votes
Category
expert
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,287.84 rating
Confidence interval: 1,251.15 – 1,324.54
222 votes
Category
german
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,285.56 rating
Confidence interval: 1,272.07 – 1,299.05
1669 votes
Category
hard_prompts
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
gpt-4.1-nano-2025-04-14
1,292.45 rating
Confidence interval: 1,275.46 – 1,309.44
1062 votes
Category
hard_prompts_english
Evaluated configuration
gpt-4.1-nano-2025-04-14
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating