codellama-34b-instruct
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelscodellama-34b-instruct
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
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 · 2026-10-15 · rating
codellama-34b-instruct
976.44 rating
Confidence interval: 938.86 – 1,014.02
249 votes
- Category
- chinese
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,045.62 rating
Confidence interval: 1,025.51 – 1,065.73
853 votes
- Category
- coding
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,031.46 rating
Confidence interval: 1,014.84 – 1,048.07
1507 votes
- Category
- creative_writing
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,091.94 rating
Confidence interval: 1,082.29 – 1,101.58
5804 votes
- Category
- english
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
codellama-34b-instruct
882.58 rating
Confidence interval: 870.00 – 895.15
5094 votes
- Category
- exclude_ties
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,031.95 rating
Confidence interval: 1,017.42 – 1,046.47
1540 votes
- Category
- hard_prompts
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,046.79 rating
Confidence interval: 1,030.88 – 1,062.71
1278 votes
- Category
- hard_prompts_english
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,033.60 rating
Confidence interval: 1,009.20 – 1,058.01
639 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,014.67 rating
Confidence interval: 997.88 – 1,031.45
1375 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,064.05 rating
Confidence interval: 1,031.65 – 1,096.44
383 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,066.41 rating
Confidence interval: 1,048.82 – 1,084.01
1225 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,054.96 rating
Confidence interval: 1,033.78 – 1,076.15
667 votes
- Category
- industry_mathematical
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,025.82 rating
Confidence interval: 993.91 – 1,057.74
340 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,062.89 rating
Confidence interval: 1,048.09 – 1,077.70
1769 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,048.30 rating
Confidence interval: 1,033.80 – 1,062.79
2003 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,027.77 rating
Confidence interval: 1,014.99 – 1,040.56
2294 votes
- Category
- instruction_following
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,013.14 rating
Confidence interval: 980.65 – 1,045.63
320 votes
- Category
- longer_query
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,056.37 rating
Confidence interval: 1,037.24 – 1,075.51
770 votes
- Category
- math
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,015.35 rating
Confidence interval: 996.99 – 1,033.71
1155 votes
- Category
- multi_turn
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,010.58 rating
Confidence interval: 994.94 – 1,026.22
1562 votes
- Category
- non_english
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
codellama-34b-instruct
1,065.44 rating
Confidence interval: 1,056.68 – 1,074.20
7366 votes
- Category
- overall
- Evaluated configuration
- codellama-34b-instruct
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Llama 2 Community
0 selected Compare 0