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
gemma-2-9b-it
1,184.83 rating
Confidence interval: 1,175.08 – 1,194.58
4980 votes
Category
chinese
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,173.21 rating
Confidence interval: 1,166.02 – 1,180.40
8921 votes
Category
coding
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,205.28 rating
Confidence interval: 1,197.82 – 1,212.75
8340 votes
Category
creative_writing
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,219.71 rating
Confidence interval: 1,214.96 – 1,224.47
29787 votes
Category
english
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,089.97 rating
Confidence interval: 1,084.09 – 1,095.86
34710 votes
Category
exclude_ties
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,147.00 rating
Confidence interval: 1,135.20 – 1,158.80
2847 votes
Category
expert
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,190.37 rating
Confidence interval: 1,164.11 – 1,216.63
591 votes
Category
french
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,186.10 rating
Confidence interval: 1,169.77 – 1,202.44
1580 votes
Category
german
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,171.26 rating
Confidence interval: 1,165.39 – 1,177.12
14756 votes
Category
hard_prompts
Evaluated configuration
Gemma 2 9B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
gemma-2-9b-it
1,177.63 rating
Confidence interval: 1,170.50 – 1,184.75
9094 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 2 9B IT
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
gemma-2-9b-it
1,184.90 rating
Confidence interval: 1,177.88 – 1,191.92
9128 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,214.90 rating
Confidence interval: 1,203.34 – 1,226.45
3243 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,203.48 rating
Confidence interval: 1,196.15 – 1,210.82
9169 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,193.17 rating
Confidence interval: 1,185.04 – 1,201.30
6297 votes
Category
industry_mathematical
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,165.40 rating
Confidence interval: 1,152.73 – 1,178.06
2812 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,196.56 rating
Confidence interval: 1,190.48 – 1,202.63
14591 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,218.99 rating
Confidence interval: 1,212.98 – 1,225.00
14640 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,178.05 rating
Confidence interval: 1,172.79 – 1,183.30
21359 votes
Category
instruction_following
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,144.21 rating
Confidence interval: 1,126.53 – 1,161.88
1301 votes
Category
japanese
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,136.69 rating
Confidence interval: 1,115.55 – 1,157.83
1087 votes
Category
korean
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,196.39 rating
Confidence interval: 1,188.61 – 1,204.17
6877 votes
Category
longer_query
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,183.12 rating
Confidence interval: 1,175.46 – 1,190.78
7110 votes
Category
math
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,193.38 rating
Confidence interval: 1,186.10 – 1,200.65
9730 votes
Category
multi_turn
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,187.78 rating
Confidence interval: 1,182.84 – 1,192.72
24824 votes
Category
non_english
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,207.36 rating
Confidence interval: 1,203.56 – 1,211.16
54611 votes
Category
overall
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,200.38 rating
Confidence interval: 1,192.29 – 1,208.48
6684 votes
Category
russian
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
gemma-2-9b-it
1,200.22 rating
Confidence interval: 1,174.37 – 1,226.07
614 votes
Category
spanish
Evaluated configuration
gemma-2-9b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
gemma-2-9b-it
17.2 GiB checkpoint tensor payload · 9.24 B stored tensor elements · BF16
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.