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-2b-it
985.83 rating
Confidence interval: 960.56 – 1,011.11
598 votes
Category
chinese
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
gemma-2b-it
1,009.33 rating
Confidence interval: 987.58 – 1,031.07
742 votes
Category
coding
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
gemma-2b-it
986.14 rating
Confidence interval: 963.12 – 1,009.16
696 votes
Category
creative_writing
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
gemma-2b-it
1,032.75 rating
Confidence interval: 1,019.51 – 1,045.99
3028 votes
Category
english
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
gemma-2b-it
779.56 rating
Confidence interval: 761.52 – 797.60
3331 votes
Category
exclude_ties
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
gemma-2b-it
988.64 rating
Confidence interval: 971.36 – 1,005.92
1191 votes
Category
hard_prompts
Evaluated configuration
Gemma 2B IT
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
gemma-2b-it
995.91 rating
Confidence interval: 975.96 – 1,015.87
832 votes
Category
hard_prompts_english
Evaluated configuration
Gemma 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-2b-it
967.68 rating
Confidence interval: 945.20 – 990.15
677 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gemma-2b-it
1,019.35 rating
Confidence interval: 981.34 – 1,057.36
273 votes
Category
industry_legal_and_government
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gemma-2b-it
949.67 rating
Confidence interval: 927.00 – 972.35
879 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gemma-2b-it
1,004.22 rating
Confidence interval: 979.75 – 1,028.68
525 votes
Category
industry_mathematical
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gemma-2b-it
938.25 rating
Confidence interval: 901.29 – 975.21
292 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gemma-2b-it
1,019.80 rating
Confidence interval: 1,002.16 – 1,037.44
1285 votes
Category
industry_software_and_it_services
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gemma-2b-it
978.28 rating
Confidence interval: 959.78 – 996.79
1152 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gemma-2b-it
970.30 rating
Confidence interval: 954.30 – 986.29
1522 votes
Category
instruction_following
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gemma-2b-it
980.42 rating
Confidence interval: 950.94 – 1,009.90
377 votes
Category
longer_query
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gemma-2b-it
1,008.63 rating
Confidence interval: 986.72 – 1,030.54
597 votes
Category
math
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gemma-2b-it
944.83 rating
Confidence interval: 921.52 – 968.13
768 votes
Category
multi_turn
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gemma-2b-it
957.89 rating
Confidence interval: 942.05 – 973.72
1752 votes
Category
non_english
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gemma-2b-it
1,002.11 rating
Confidence interval: 990.63 – 1,013.58
4780 votes
Category
overall
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gemma-2b-it
936.60 rating
Confidence interval: 900.68 – 972.51
300 votes
Category
russian
Evaluated configuration
gemma-2b-it
Evaluation type
human preference
Run it locally
Inference · memory estimate
gemma-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.