Llama 3.2 1B Instruct
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.
GeekRadar / The comparison desk
COMPARE.
AI modelsLlama 3.2 1B Instruct
AI model Released
- Context window
- 131,072 tokens
- Maximum output
- 32,000 tokens
- Open weights
- Yes
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 · 2026-10-28 · rating
Llama 3.2 1B Instruct
958.59 rating
Confidence interval: 932.34 – 984.84
674 votes
- Category
- chinese
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,070.23 rating
Confidence interval: 1,054.46 – 1,085.99
1346 votes
- Category
- coding
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,032.48 rating
Confidence interval: 1,012.71 – 1,052.24
1091 votes
- Category
- creative_writing
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,116.63 rating
Confidence interval: 1,106.95 – 1,126.31
4320 votes
- Category
- english
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
822.76 rating
Confidence interval: 807.15 – 838.37
5619 votes
- Category
- exclude_ties
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,006.98 rating
Confidence interval: 980.01 – 1,033.95
487 votes
- Category
- expert
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,013.69 rating
Confidence interval: 973.95 – 1,053.42
247 votes
- Category
- german
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,044.14 rating
Confidence interval: 1,031.63 – 1,056.64
2247 votes
- Category
- hard_prompts
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,086.71 rating
Confidence interval: 1,071.79 – 1,101.64
1437 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
999.59 rating
Confidence interval: 979.14 – 1,020.03
1044 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,025.03 rating
Confidence interval: 1,006.68 – 1,043.38
1151 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,070.71 rating
Confidence interval: 1,041.69 – 1,099.73
489 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,054.59 rating
Confidence interval: 1,036.76 – 1,072.42
1407 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,097.96 rating
Confidence interval: 1,080.14 – 1,115.79
976 votes
- Category
- industry_mathematical
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,009.02 rating
Confidence interval: 977.92 – 1,040.12
445 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,056.14 rating
Confidence interval: 1,042.87 – 1,069.42
2184 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,029.68 rating
Confidence interval: 1,014.99 – 1,044.37
2047 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,030.93 rating
Confidence interval: 1,019.85 – 1,042.02
3248 votes
- Category
- instruction_following
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,049.49 rating
Confidence interval: 1,030.92 – 1,068.05
1057 votes
- Category
- longer_query
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,085.70 rating
Confidence interval: 1,069.69 – 1,101.72
1162 votes
- Category
- math
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,029.83 rating
Confidence interval: 1,011.32 – 1,048.34
1236 votes
- Category
- multi_turn
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
973.19 rating
Confidence interval: 961.60 – 984.78
3725 votes
- Category
- non_english
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
1,054.61 rating
Confidence interval: 1,046.91 – 1,062.31
8045 votes
- Category
- overall
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Llama 3.2 1B Instruct
941.01 rating
Confidence interval: 918.45 – 963.56
953 votes
- Category
- russian
- Evaluated configuration
- Llama 3.2 1B Instruct
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
958.64 rating
Confidence interval: 932.38 – 984.90
674 votes
- Category
- chinese
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,070.33 rating
Confidence interval: 1,054.56 – 1,086.10
1346 votes
- Category
- coding
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,032.63 rating
Confidence interval: 1,012.86 – 1,052.40
1091 votes
- Category
- creative_writing
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,116.58 rating
Confidence interval: 1,106.90 – 1,126.26
4320 votes
- Category
- english
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
822.78 rating
Confidence interval: 807.16 – 838.39
5619 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,007.02 rating
Confidence interval: 980.04 – 1,034.00
487 votes
- Category
- expert
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,013.69 rating
Confidence interval: 973.97 – 1,053.40
247 votes
- Category
- german
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,044.13 rating
Confidence interval: 1,031.62 – 1,056.64
2247 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,086.60 rating
Confidence interval: 1,071.67 – 1,101.53
1437 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
999.63 rating
Confidence interval: 979.18 – 1,020.08
1044 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,025.09 rating
Confidence interval: 1,006.73 – 1,043.44
1151 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,070.46 rating
Confidence interval: 1,041.43 – 1,099.49
489 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,054.57 rating
Confidence interval: 1,036.73 – 1,072.40
1407 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,097.96 rating
Confidence interval: 1,080.13 – 1,115.78
976 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,009.08 rating
Confidence interval: 977.97 – 1,040.19
445 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,056.22 rating
Confidence interval: 1,042.95 – 1,069.50
2184 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,029.74 rating
Confidence interval: 1,015.05 – 1,044.43
2047 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,030.94 rating
Confidence interval: 1,019.86 – 1,042.03
3248 votes
- Category
- instruction_following
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,049.53 rating
Confidence interval: 1,030.96 – 1,068.10
1057 votes
- Category
- longer_query
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,085.66 rating
Confidence interval: 1,069.65 – 1,101.68
1162 votes
- Category
- math
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,029.83 rating
Confidence interval: 1,011.32 – 1,048.34
1236 votes
- Category
- multi_turn
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
973.28 rating
Confidence interval: 961.69 – 984.88
3725 votes
- Category
- non_english
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
1,054.60 rating
Confidence interval: 1,046.90 – 1,062.29
8045 votes
- Category
- overall
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Llama 3.2 1B Instruct
941.16 rating
Confidence interval: 918.60 – 963.72
953 votes
- Category
- russian
- Evaluated configuration
- llama-3.2-1b-instruct
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Llama 3.2 1B Instruct
Capabilities
- Context window
- 131,072 tokens
- Maximum output
- 32,000 tokens
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Knowledge cutoff
- 2023-12
- Model license
- Llama 3.2 Community License
- Checkpoint tensor payload
- 2.30 GiB
Input modalities
- text
Output modalities
- text
0 selected Compare 0