llama-3-8b-instruct
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsllama-3-8b-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
llama-3-8b-instruct
1,076.04 rating
Confidence interval: 1,066.26 – 1,085.83
10757 votes
- Category
- chinese
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,151.41 rating
Confidence interval: 1,143.89 – 1,158.93
18374 votes
- Category
- coding
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,149.66 rating
Confidence interval: 1,141.56 – 1,157.76
15365 votes
- Category
- creative_writing
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,213.17 rating
Confidence interval: 1,208.30 – 1,218.03
61703 votes
- Category
- english
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,029.97 rating
Confidence interval: 1,024.00 – 1,035.95
67687 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,113.08 rating
Confidence interval: 1,101.37 – 1,124.79
5360 votes
- Category
- expert
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,158.82 rating
Confidence interval: 1,137.02 – 1,180.61
1624 votes
- Category
- french
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,104.42 rating
Confidence interval: 1,089.60 – 1,119.24
3370 votes
- Category
- german
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,133.12 rating
Confidence interval: 1,127.05 – 1,139.19
30221 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,163.52 rating
Confidence interval: 1,156.34 – 1,170.70
19891 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,127.11 rating
Confidence interval: 1,118.10 – 1,136.12
10764 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,132.00 rating
Confidence interval: 1,124.23 – 1,139.76
15413 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,167.51 rating
Confidence interval: 1,155.88 – 1,179.14
5578 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,170.02 rating
Confidence interval: 1,162.12 – 1,177.91
17322 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,153.29 rating
Confidence interval: 1,145.06 – 1,161.52
12836 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,148.00 rating
Confidence interval: 1,135.85 – 1,160.14
5400 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,156.04 rating
Confidence interval: 1,149.57 – 1,162.52
29645 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,147.80 rating
Confidence interval: 1,141.16 – 1,154.44
25481 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,127.04 rating
Confidence interval: 1,121.39 – 1,132.69
37733 votes
- Category
- instruction_following
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
llama-3-8b-instruct
967.40 rating
Confidence interval: 949.21 – 985.60
1992 votes
- Category
- japanese
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,003.58 rating
Confidence interval: 984.36 – 1,022.79
2422 votes
- Category
- korean
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,127.44 rating
Confidence interval: 1,118.87 – 1,136.00
11165 votes
- Category
- longer_query
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,151.16 rating
Confidence interval: 1,143.31 – 1,159.01
14252 votes
- Category
- math
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,152.45 rating
Confidence interval: 1,144.35 – 1,160.54
14815 votes
- Category
- multi_turn
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,097.54 rating
Confidence interval: 1,092.19 – 1,102.89
42939 votes
- Category
- non_english
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,165.56 rating
Confidence interval: 1,161.85 – 1,169.28
104642 votes
- Category
- overall
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,136.99 rating
Confidence interval: 1,083.86 – 1,190.12
257 votes
- Category
- polish
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,109.24 rating
Confidence interval: 1,100.24 – 1,118.25
10009 votes
- Category
- russian
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
llama-3-8b-instruct
1,172.74 rating
Confidence interval: 1,151.53 – 1,193.94
1744 votes
- Category
- spanish
- Evaluated configuration
- llama-3-8b-instruct
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Llama 3 Community
0 selected Compare 0