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 27B
1,220.89 rating
Confidence interval: 1,212.09 – 1,229.70
6872 votes
Category
chinese
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Gemma 2 27B
1,210.64 rating
Confidence interval: 1,204.29 – 1,216.99
12088 votes
Category
coding
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Gemma 2 27B
1,240.33 rating
Confidence interval: 1,233.49 – 1,247.17
11429 votes
Category
creative_writing
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Gemma 2 27B
1,241.90 rating
Confidence interval: 1,237.60 – 1,246.19
41283 votes
Category
english
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Gemma 2 27B
1,128.53 rating
Confidence interval: 1,123.34 – 1,133.72
47955 votes
Category
exclude_ties
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Gemma 2 27B
1,171.25 rating
Confidence interval: 1,160.80 – 1,181.70
4025 votes
Category
expert
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Gemma 2 27B
1,247.75 rating
Confidence interval: 1,224.42 – 1,271.08
793 votes
Category
french
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Gemma 2 27B
1,208.93 rating
Confidence interval: 1,194.31 – 1,223.54
2037 votes
Category
german
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Gemma 2 27B
1,198.23 rating
Confidence interval: 1,193.04 – 1,203.41
20494 votes
Category
hard_prompts
Evaluated configuration
Gemma 2 27B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Gemma 2 27B
1,205.75 rating
Confidence interval: 1,199.47 – 1,212.04
12606 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 2 27B 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 27B
1,212.47 rating
Confidence interval: 1,206.04 – 1,218.90
12280 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Gemma 2 27B
1,240.96 rating
Confidence interval: 1,230.53 – 1,251.38
4458 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Gemma 2 27B
1,228.04 rating
Confidence interval: 1,221.48 – 1,234.61
12863 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,221.42 rating
Confidence interval: 1,214.20 – 1,228.64
8869 votes
Category
industry_mathematical
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Gemma 2 27B
1,197.63 rating
Confidence interval: 1,186.31 – 1,208.95
3862 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Gemma 2 27B
1,227.89 rating
Confidence interval: 1,222.45 – 1,233.32
19950 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Gemma 2 27B
1,248.72 rating
Confidence interval: 1,243.21 – 1,254.23
20390 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Gemma 2 27B
1,205.86 rating
Confidence interval: 1,201.12 – 1,210.61
29545 votes
Category
instruction_following
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Gemma 2 27B
1,175.38 rating
Confidence interval: 1,159.53 – 1,191.22
1808 votes
Category
japanese
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,173.81 rating
Confidence interval: 1,154.56 – 1,193.07
1440 votes
Category
korean
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,230.29 rating
Confidence interval: 1,223.40 – 1,237.19
9918 votes
Category
longer_query
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,211.93 rating
Confidence interval: 1,205.07 – 1,218.80
10170 votes
Category
math
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,223.69 rating
Confidence interval: 1,217.16 – 1,230.23
13588 votes
Category
multi_turn
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,216.96 rating
Confidence interval: 1,212.51 – 1,221.40
34471 votes
Category
non_english
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,231.34 rating
Confidence interval: 1,227.97 – 1,234.71
75754 votes
Category
overall
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,277.27 rating
Confidence interval: 1,204.05 – 1,350.49
58 votes
Category
polish
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,233.85 rating
Confidence interval: 1,226.63 – 1,241.07
9678 votes
Category
russian
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Gemma 2 27B
1,228.18 rating
Confidence interval: 1,205.39 – 1,250.98
845 votes
Category
spanish
Evaluated configuration
gemma-2-27b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
Gemma 2 27B
50.7 GiB checkpoint tensor payload · 27.23 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.
API cost
USD / month
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.