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
Aya Expanse 8B
1,180.87 rating
Confidence interval: 1,157.59 – 1,204.16
618 votes
Category
chinese
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,160.23 rating
Confidence interval: 1,145.80 – 1,174.66
1567 votes
Category
coding
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,167.75 rating
Confidence interval: 1,152.82 – 1,182.68
1528 votes
Category
creative_writing
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,190.79 rating
Confidence interval: 1,182.10 – 1,199.48
5497 votes
Category
english
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,052.53 rating
Confidence interval: 1,040.94 – 1,064.13
6336 votes
Category
exclude_ties
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,152.38 rating
Confidence interval: 1,128.93 – 1,175.83
600 votes
Category
expert
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,187.63 rating
Confidence interval: 1,150.37 – 1,224.89
240 votes
Category
german
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,155.81 rating
Confidence interval: 1,144.57 – 1,167.04
2576 votes
Category
hard_prompts
Evaluated configuration
Aya Expanse 8B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Aya Expanse 8B
1,153.82 rating
Confidence interval: 1,139.50 – 1,168.14
1620 votes
Category
hard_prompts_english
Evaluated configuration
Aya Expanse 8B
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
Aya Expanse 8B
1,149.85 rating
Confidence interval: 1,136.18 – 1,163.52
1784 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,224.65 rating
Confidence interval: 1,199.75 – 1,249.55
551 votes
Category
industry_legal_and_government
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,203.63 rating
Confidence interval: 1,189.34 – 1,217.91
1689 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,176.42 rating
Confidence interval: 1,160.41 – 1,192.42
1146 votes
Category
industry_mathematical
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,202.99 rating
Confidence interval: 1,176.11 – 1,229.86
470 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,176.78 rating
Confidence interval: 1,164.95 – 1,188.61
2471 votes
Category
industry_software_and_it_services
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,185.49 rating
Confidence interval: 1,174.30 – 1,196.68
2746 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,154.70 rating
Confidence interval: 1,145.19 – 1,164.22
4006 votes
Category
instruction_following
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,120.26 rating
Confidence interval: 1,084.66 – 1,155.86
231 votes
Category
japanese
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,191.15 rating
Confidence interval: 1,176.44 – 1,205.87
1483 votes
Category
longer_query
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,168.05 rating
Confidence interval: 1,152.98 – 1,183.12
1307 votes
Category
math
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,159.60 rating
Confidence interval: 1,145.23 – 1,173.97
1746 votes
Category
multi_turn
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,179.99 rating
Confidence interval: 1,170.86 – 1,189.12
4321 votes
Category
non_english
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,185.07 rating
Confidence interval: 1,178.16 – 1,191.99
9818 votes
Category
overall
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Aya Expanse 8B
1,197.27 rating
Confidence interval: 1,182.57 – 1,211.96
1474 votes
Category
russian
Evaluated configuration
c4ai-aya-expanse-8b
Evaluation type
human preference
Run it locally
Inference · memory estimate
Aya Expanse 8B
15.0 GiB checkpoint tensor payload · 8.03 B stored tensor elements · F16
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.