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-7b-it
1,035.39 rating
Confidence interval: 1,015.69 – 1,055.09
1049 votes
Category
chinese
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
gemma-7b-it
1,047.85 rating
Confidence interval: 1,031.46 – 1,064.24
1381 votes
Category
coding
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
gemma-7b-it
1,023.20 rating
Confidence interval: 1,005.62 – 1,040.78
1345 votes
Category
creative_writing
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
gemma-7b-it
1,090.05 rating
Confidence interval: 1,078.97 – 1,101.13
5689 votes
Category
english
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
gemma-7b-it
863.70 rating
Confidence interval: 849.45 – 877.95
5988 votes
Category
exclude_ties
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
gemma-7b-it
1,001.22 rating
Confidence interval: 970.36 – 1,032.09
340 votes
Category
expert
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
gemma-7b-it
1,025.41 rating
Confidence interval: 977.40 – 1,073.42
199 votes
Category
french
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
gemma-7b-it
1,041.51 rating
Confidence interval: 1,028.14 – 1,054.88
2267 votes
Category
hard_prompts
Evaluated configuration
Gemma 7B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
gemma-7b-it
1,060.57 rating
Confidence interval: 1,045.39 – 1,075.75
1588 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 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-7b-it
1,001.40 rating
Confidence interval: 983.85 – 1,018.95
1291 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gemma-7b-it
1,044.15 rating
Confidence interval: 1,015.49 – 1,072.81
462 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gemma-7b-it
1,020.27 rating
Confidence interval: 1,003.11 – 1,037.43
1588 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gemma-7b-it
1,061.27 rating
Confidence interval: 1,043.70 – 1,078.84
982 votes
Category
industry_mathematical
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gemma-7b-it
1,027.81 rating
Confidence interval: 1,002.29 – 1,053.33
538 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gemma-7b-it
1,059.68 rating
Confidence interval: 1,045.77 – 1,073.59
2374 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gemma-7b-it
1,033.78 rating
Confidence interval: 1,019.23 – 1,048.34
2191 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gemma-7b-it
1,016.89 rating
Confidence interval: 1,004.15 – 1,029.62
2835 votes
Category
instruction_following
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gemma-7b-it
1,021.43 rating
Confidence interval: 999.19 – 1,043.67
676 votes
Category
longer_query
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gemma-7b-it
1,066.29 rating
Confidence interval: 1,049.88 – 1,082.70
1120 votes
Category
math
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gemma-7b-it
963.20 rating
Confidence interval: 944.49 – 981.92
1332 votes
Category
multi_turn
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gemma-7b-it
998.58 rating
Confidence interval: 986.36 – 1,010.80
3236 votes
Category
non_english
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gemma-7b-it
1,056.11 rating
Confidence interval: 1,046.59 – 1,065.64
8925 votes
Category
overall
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gemma-7b-it
993.27 rating
Confidence interval: 969.95 – 1,016.58
629 votes
Category
russian
Evaluated configuration
gemma-7b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
gemma-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.