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-1.1-2b-it
1,011.47 rating
Confidence interval: 993.56 – 1,029.39
1291 votes
Category
chinese
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
1,033.86 rating
Confidence interval: 1,019.97 – 1,047.74
1963 votes
Category
coding
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
997.68 rating
Confidence interval: 980.84 – 1,014.52
1486 votes
Category
creative_writing
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
1,050.22 rating
Confidence interval: 1,040.50 – 1,059.95
5934 votes
Category
english
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
796.33 rating
Confidence interval: 782.86 – 809.80
7496 votes
Category
exclude_ties
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
970.07 rating
Confidence interval: 944.45 – 995.70
578 votes
Category
expert
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
943.83 rating
Confidence interval: 908.93 – 978.74
365 votes
Category
german
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
1,004.84 rating
Confidence interval: 993.10 – 1,016.57
3183 votes
Category
hard_prompts
Evaluated configuration
Gemma 1.1 2B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
gemma-1.1-2b-it
1,025.81 rating
Confidence interval: 1,011.49 – 1,040.13
1941 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 1.1 2B 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-1.1-2b-it
979.90 rating
Confidence interval: 963.26 – 996.54
1499 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
995.11 rating
Confidence interval: 967.09 – 1,023.13
578 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
995.90 rating
Confidence interval: 979.75 – 1,012.04
1929 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,042.77 rating
Confidence interval: 1,025.66 – 1,059.88
1224 votes
Category
industry_mathematical
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
990.36 rating
Confidence interval: 963.65 – 1,017.06
628 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,031.88 rating
Confidence interval: 1,019.99 – 1,043.78
3194 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,006.01 rating
Confidence interval: 992.93 – 1,019.09
2596 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
991.68 rating
Confidence interval: 980.80 – 1,002.56
3877 votes
Category
instruction_following
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
898.94 rating
Confidence interval: 866.10 – 931.78
386 votes
Category
korean
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,002.41 rating
Confidence interval: 984.68 – 1,020.13
1179 votes
Category
longer_query
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,047.13 rating
Confidence interval: 1,031.22 – 1,063.03
1355 votes
Category
math
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
958.49 rating
Confidence interval: 940.63 – 976.35
1478 votes
Category
multi_turn
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
988.42 rating
Confidence interval: 978.33 – 998.51
4920 votes
Category
non_english
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
1,022.18 rating
Confidence interval: 1,014.52 – 1,029.85
10854 votes
Category
overall
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gemma-1.1-2b-it
990.32 rating
Confidence interval: 971.95 – 1,008.69
1166 votes
Category
russian
Evaluated configuration
gemma-1.1-2b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
gemma-1.1-2b-it
4.7 GiB checkpoint tensor payload · 2.51 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.