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
Hy3
1,481.01 rating
Confidence interval: 1,462.76 – 1,499.26
1065 votes
Category
chinese
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Hy3
1,466.36 rating
Confidence interval: 1,456.49 – 1,476.22
3772 votes
Category
coding
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Hy3
1,406.98 rating
Confidence interval: 1,395.16 – 1,418.81
2750 votes
Category
creative_writing
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Hy3
1,446.64 rating
Confidence interval: 1,438.26 – 1,455.03
5260 votes
Category
english
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Hy3
1,433.19 rating
Confidence interval: 1,425.49 – 1,440.90
10169 votes
Category
exclude_ties
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Hy3
1,457.18 rating
Confidence interval: 1,441.82 – 1,472.54
1462 votes
Category
expert
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Hy3
1,447.21 rating
Confidence interval: 1,420.93 – 1,473.49
567 votes
Category
french
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Hy3
1,436.88 rating
Confidence interval: 1,401.95 – 1,471.81
252 votes
Category
german
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Hy3
1,447.99 rating
Confidence interval: 1,441.09 – 1,454.89
9155 votes
Category
hard_prompts
Evaluated configuration
Hy3
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Hy3
1,453.65 rating
Confidence interval: 1,443.52 – 1,463.77
3521 votes
Category
hard_prompts_english
Evaluated configuration
Hy3
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 · 2026-10-15 · rating
Hy3
1,398.15 rating
Confidence interval: 1,386.87 – 1,409.44
3012 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Hy3
1,419.95 rating
Confidence interval: 1,400.36 – 1,439.55
940 votes
Category
industry_legal_and_government
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Hy3
1,459.86 rating
Confidence interval: 1,446.41 – 1,473.32
1929 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Hy3
1,480.50 rating
Confidence interval: 1,458.94 – 1,502.05
723 votes
Category
industry_mathematical
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Hy3
1,454.58 rating
Confidence interval: 1,433.43 – 1,475.73
787 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Hy3
1,463.08 rating
Confidence interval: 1,454.33 – 1,471.82
4830 votes
Category
industry_software_and_it_services
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Hy3
1,414.12 rating
Confidence interval: 1,403.43 – 1,424.82
3247 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Hy3
1,425.85 rating
Confidence interval: 1,416.63 – 1,435.08
4417 votes
Category
instruction_following
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Hy3
1,396.34 rating
Confidence interval: 1,355.81 – 1,436.86
221 votes
Category
japanese
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Hy3
1,397.33 rating
Confidence interval: 1,360.89 – 1,433.78
262 votes
Category
korean
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Hy3
1,440.67 rating
Confidence interval: 1,432.10 – 1,449.24
5528 votes
Category
longer_query
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Hy3
1,470.85 rating
Confidence interval: 1,448.47 – 1,493.24
662 votes
Category
math
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Hy3
1,434.68 rating
Confidence interval: 1,421.01 – 1,448.35
1965 votes
Category
multi_turn
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Hy3
1,426.29 rating
Confidence interval: 1,418.96 – 1,433.63
7548 votes
Category
non_english
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Hy3
1,438.00 rating
Confidence interval: 1,431.87 – 1,444.13
12208 votes
Category
overall
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Hy3
1,449.91 rating
Confidence interval: 1,413.29 – 1,486.52
236 votes
Category
polish
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Hy3
1,431.22 rating
Confidence interval: 1,415.95 – 1,446.50
1516 votes
Category
russian
Evaluated configuration
hy3
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Hy3
1,457.74 rating
Confidence interval: 1,429.86 – 1,485.61
437 votes
Category
spanish
Evaluated configuration
hy3
Evaluation type
human preference
Run it locally
Inference · memory estimate
Hy3
Not enough verified architecture information for a reliable VRAM estimate.
API cost
USD / month
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.