Llama-3.1-8B-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-3.1-8B-Instruct
AI model Released
- Context window
- 128,000 tokens
- Maximum output
- 4,096 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-3.1-8B-Instruct
1,150.72 rating
Confidence interval: 1,140.24 – 1,161.21
4400 votes
- Category
- chinese
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,194.52 rating
Confidence interval: 1,187.10 – 1,201.93
8582 votes
- Category
- coding
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,154.01 rating
Confidence interval: 1,145.71 – 1,162.31
7346 votes
- Category
- creative_writing
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,217.51 rating
Confidence interval: 1,212.37 – 1,222.66
26610 votes
- Category
- english
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,054.92 rating
Confidence interval: 1,048.34 – 1,061.49
31686 votes
- Category
- exclude_ties
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,143.77 rating
Confidence interval: 1,131.58 – 1,155.96
2589 votes
- Category
- expert
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,177.80 rating
Confidence interval: 1,148.03 – 1,207.56
478 votes
- Category
- french
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,144.28 rating
Confidence interval: 1,126.37 – 1,162.19
1295 votes
- Category
- german
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,174.56 rating
Confidence interval: 1,168.45 – 1,180.66
13535 votes
- Category
- hard_prompts
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,195.55 rating
Confidence interval: 1,188.05 – 1,203.04
8195 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,165.90 rating
Confidence interval: 1,156.96 – 1,174.85
5722 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,144.55 rating
Confidence interval: 1,136.70 – 1,152.41
7706 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,206.33 rating
Confidence interval: 1,194.02 – 1,218.64
2882 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,193.24 rating
Confidence interval: 1,185.37 – 1,201.11
8403 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,180.16 rating
Confidence interval: 1,171.70 – 1,188.62
5985 votes
- Category
- industry_mathematical
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,181.50 rating
Confidence interval: 1,168.36 – 1,194.64
2564 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,194.85 rating
Confidence interval: 1,188.35 – 1,201.35
13139 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,162.00 rating
Confidence interval: 1,155.41 – 1,168.59
13505 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,158.80 rating
Confidence interval: 1,153.29 – 1,164.32
19781 votes
- Category
- instruction_following
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,061.07 rating
Confidence interval: 1,041.79 – 1,080.35
1234 votes
- Category
- japanese
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,052.72 rating
Confidence interval: 1,028.55 – 1,076.90
802 votes
- Category
- korean
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,181.28 rating
Confidence interval: 1,173.28 – 1,189.27
6736 votes
- Category
- longer_query
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,179.20 rating
Confidence interval: 1,171.22 – 1,187.18
7135 votes
- Category
- math
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,171.97 rating
Confidence interval: 1,164.27 – 1,179.68
8930 votes
- Category
- multi_turn
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,147.93 rating
Confidence interval: 1,142.66 – 1,153.20
22995 votes
- Category
- non_english
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,186.55 rating
Confidence interval: 1,182.45 – 1,190.65
49605 votes
- Category
- overall
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,158.15 rating
Confidence interval: 1,149.74 – 1,166.57
6589 votes
- Category
- russian
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Llama-3.1-8B-Instruct
1,169.26 rating
Confidence interval: 1,141.99 – 1,196.52
565 votes
- Category
- spanish
- Evaluated configuration
- Llama 3.1 8B Instruct
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,150.77 rating
Confidence interval: 1,140.28 – 1,161.26
4400 votes
- Category
- chinese
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,194.62 rating
Confidence interval: 1,187.20 – 1,202.03
8582 votes
- Category
- coding
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,154.16 rating
Confidence interval: 1,145.86 – 1,162.47
7346 votes
- Category
- creative_writing
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,217.46 rating
Confidence interval: 1,212.31 – 1,222.60
26610 votes
- Category
- english
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,054.93 rating
Confidence interval: 1,048.35 – 1,061.50
31686 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,143.81 rating
Confidence interval: 1,131.61 – 1,156.00
2589 votes
- Category
- expert
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,177.48 rating
Confidence interval: 1,147.71 – 1,207.26
478 votes
- Category
- french
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,144.28 rating
Confidence interval: 1,126.42 – 1,162.14
1295 votes
- Category
- german
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,174.55 rating
Confidence interval: 1,168.44 – 1,180.65
13535 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,195.43 rating
Confidence interval: 1,187.94 – 1,202.93
8195 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,165.94 rating
Confidence interval: 1,156.99 – 1,174.89
5722 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,144.61 rating
Confidence interval: 1,136.75 – 1,152.47
7706 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,206.08 rating
Confidence interval: 1,193.77 – 1,218.39
2882 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,193.22 rating
Confidence interval: 1,185.35 – 1,201.09
8403 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,180.15 rating
Confidence interval: 1,171.70 – 1,188.61
5985 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,181.56 rating
Confidence interval: 1,168.42 – 1,194.70
2564 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,194.93 rating
Confidence interval: 1,188.43 – 1,201.44
13139 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,162.07 rating
Confidence interval: 1,155.48 – 1,168.66
13505 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,158.81 rating
Confidence interval: 1,153.30 – 1,164.33
19781 votes
- Category
- instruction_following
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,060.90 rating
Confidence interval: 1,041.69 – 1,080.11
1234 votes
- Category
- japanese
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,052.76 rating
Confidence interval: 1,028.61 – 1,076.92
802 votes
- Category
- korean
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,181.32 rating
Confidence interval: 1,173.32 – 1,189.32
6736 votes
- Category
- longer_query
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,179.16 rating
Confidence interval: 1,171.18 – 1,187.14
7135 votes
- Category
- math
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,171.97 rating
Confidence interval: 1,164.26 – 1,179.68
8930 votes
- Category
- multi_turn
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,148.02 rating
Confidence interval: 1,142.76 – 1,153.29
22995 votes
- Category
- non_english
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,186.54 rating
Confidence interval: 1,182.44 – 1,190.64
49605 votes
- Category
- overall
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,158.31 rating
Confidence interval: 1,149.89 – 1,166.72
6589 votes
- Category
- russian
- Evaluated configuration
- llama-3.1-8b-instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Llama-3.1-8B-Instruct
1,169.18 rating
Confidence interval: 1,141.89 – 1,196.46
565 votes
- Category
- spanish
- Evaluated configuration
- llama-3.1-8b-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-3.1-8B-Instruct
Capabilities
- Context window
- 128,000 tokens
- Maximum output
- 4,096 tokens
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Knowledge cutoff
- 2023-12
- Checkpoint tensor payload
- 14.96 GiB
Input modalities
- text
Output modalities
- text
0 selected Compare 0