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 4 Argon
1,600.18 rating
Confidence interval: 1,579.81 – 1,620.56
918 votes
Category
chinese
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,538.20 rating
Confidence interval: 1,526.66 – 1,549.75
2813 votes
Category
coding
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,527.42 rating
Confidence interval: 1,514.77 – 1,540.07
2720 votes
Category
creative_writing
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,528.99 rating
Confidence interval: 1,519.65 – 1,538.33
4532 votes
Category
english
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,555.15 rating
Confidence interval: 1,546.65 – 1,563.65
8908 votes
Category
exclude_ties
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,548.97 rating
Confidence interval: 1,531.74 – 1,566.21
1219 votes
Category
expert
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,550.09 rating
Confidence interval: 1,522.03 – 1,578.15
517 votes
Category
french
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,559.50 rating
Confidence interval: 1,515.27 – 1,603.72
203 votes
Category
german
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,541.73 rating
Confidence interval: 1,534.08 – 1,549.39
7454 votes
Category
hard_prompts
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,539.24 rating
Confidence interval: 1,527.60 – 1,550.88
2867 votes
Category
hard_prompts_english
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,520.05 rating
Confidence interval: 1,508.27 – 1,531.83
3157 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,537.35 rating
Confidence interval: 1,516.86 – 1,557.84
938 votes
Category
industry_legal_and_government
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,546.49 rating
Confidence interval: 1,532.43 – 1,560.55
1929 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,548.88 rating
Confidence interval: 1,527.90 – 1,569.86
765 votes
Category
industry_mathematical
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,543.56 rating
Confidence interval: 1,522.06 – 1,565.06
802 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,545.29 rating
Confidence interval: 1,535.67 – 1,554.91
4193 votes
Category
industry_software_and_it_services
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,525.95 rating
Confidence interval: 1,514.88 – 1,537.02
3448 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,532.57 rating
Confidence interval: 1,522.74 – 1,542.40
4236 votes
Category
instruction_following
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,545.73 rating
Confidence interval: 1,502.31 – 1,589.16
206 votes
Category
japanese
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,542.03 rating
Confidence interval: 1,532.81 – 1,551.25
5061 votes
Category
longer_query
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,538.48 rating
Confidence interval: 1,516.09 – 1,560.87
674 votes
Category
math
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,541.77 rating
Confidence interval: 1,526.46 – 1,557.08
1664 votes
Category
multi_turn
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,520.73 rating
Confidence interval: 1,513.05 – 1,528.41
7351 votes
Category
non_english
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,528.58 rating
Confidence interval: 1,522.35 – 1,534.81
11889 votes
Category
overall
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,537.52 rating
Confidence interval: 1,492.45 – 1,582.58
192 votes
Category
polish
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,535.30 rating
Confidence interval: 1,519.94 – 1,550.66
1632 votes
Category
russian
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Gemini 4 Argon
1,505.47 rating
Confidence interval: 1,478.86 – 1,532.08
493 votes
Category
spanish
Evaluated configuration
Gemini 4 Argon (High)
Evaluation type
human preference
Run it locally
Inference · memory estimate
Gemini 4 Argon
Closed weights. No supported local deployment or GPU requirement is published.
API cost
USD / month
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.