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-1.1-7b-it
1,060.51 rating
Confidence interval: 1,047.99 – 1,073.02
3219 votes
Category
chinese
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,083.47 rating
Confidence interval: 1,073.17 – 1,093.78
4332 votes
Category
coding
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,059.13 rating
Confidence interval: 1,047.46 – 1,070.79
3409 votes
Category
creative_writing
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,124.04 rating
Confidence interval: 1,116.88 – 1,131.20
12733 votes
Category
english
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
917.94 rating
Confidence interval: 908.95 – 926.93
15506 votes
Category
exclude_ties
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,039.18 rating
Confidence interval: 1,021.60 – 1,056.77
1247 votes
Category
expert
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,065.82 rating
Confidence interval: 1,033.28 – 1,098.36
401 votes
Category
french
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,053.68 rating
Confidence interval: 1,031.65 – 1,075.71
827 votes
Category
german
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,070.53 rating
Confidence interval: 1,062.03 – 1,079.02
6987 votes
Category
hard_prompts
Evaluated configuration
Gemma 1.1 7B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
gemma-1.1-7b-it
1,090.66 rating
Confidence interval: 1,080.36 – 1,100.96
4180 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 1.1 7B 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-1.1-7b-it
1,049.62 rating
Confidence interval: 1,038.27 – 1,060.97
3421 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,093.91 rating
Confidence interval: 1,076.62 – 1,111.20
1416 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,077.77 rating
Confidence interval: 1,066.62 – 1,088.93
4147 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,097.83 rating
Confidence interval: 1,085.86 – 1,109.79
2659 votes
Category
industry_mathematical
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,072.32 rating
Confidence interval: 1,053.83 – 1,090.82
1255 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,095.16 rating
Confidence interval: 1,086.40 – 1,103.92
7051 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,073.11 rating
Confidence interval: 1,063.86 – 1,082.37
6034 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,056.71 rating
Confidence interval: 1,048.79 – 1,064.64
8852 votes
Category
instruction_following
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
970.66 rating
Confidence interval: 940.36 – 1,000.96
449 votes
Category
japanese
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
987.89 rating
Confidence interval: 962.68 – 1,013.10
770 votes
Category
korean
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,055.40 rating
Confidence interval: 1,042.85 – 1,067.94
2649 votes
Category
longer_query
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,106.78 rating
Confidence interval: 1,095.46 – 1,118.10
3039 votes
Category
math
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,039.77 rating
Confidence interval: 1,028.10 – 1,051.45
3635 votes
Category
multi_turn
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,051.51 rating
Confidence interval: 1,044.05 – 1,058.96
11160 votes
Category
non_english
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,093.93 rating
Confidence interval: 1,087.93 – 1,099.93
23893 votes
Category
overall
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,045.84 rating
Confidence interval: 1,033.25 – 1,058.42
2709 votes
Category
russian
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
gemma-1.1-7b-it
1,049.15 rating
Confidence interval: 1,016.02 – 1,082.28
411 votes
Category
spanish
Evaluated configuration
gemma-1.1-7b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
gemma-1.1-7b-it
15.9 GiB checkpoint tensor payload · 8.54 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.