llama-3-70b-instruct
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsllama-3-70b-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-3-70b-instruct
1,114.22 rating
Confidence interval: 1,105.08 – 1,123.36
15885 votes
- Category
- chinese
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,205.94 rating
Confidence interval: 1,199.01 – 1,212.87
28126 votes
- Category
- coding
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,209.59 rating
Confidence interval: 1,202.05 – 1,217.14
22753 votes
- Category
- creative_writing
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,277.32 rating
Confidence interval: 1,272.68 – 1,281.97
90553 votes
- Category
- english
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,115.34 rating
Confidence interval: 1,109.78 – 1,120.89
103844 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,148.89 rating
Confidence interval: 1,138.10 – 1,159.67
7958 votes
- Category
- expert
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,232.21 rating
Confidence interval: 1,212.39 – 1,252.02
2499 votes
- Category
- french
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,169.05 rating
Confidence interval: 1,155.30 – 1,182.81
4991 votes
- Category
- german
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,194.73 rating
Confidence interval: 1,189.17 – 1,200.29
45956 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,230.21 rating
Confidence interval: 1,223.51 – 1,236.91
29608 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,172.30 rating
Confidence interval: 1,164.20 – 1,180.40
16626 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,195.40 rating
Confidence interval: 1,188.23 – 1,202.56
23202 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,227.62 rating
Confidence interval: 1,216.92 – 1,238.33
8328 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,225.73 rating
Confidence interval: 1,218.44 – 1,233.02
25903 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,213.48 rating
Confidence interval: 1,205.69 – 1,221.26
18728 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,214.02 rating
Confidence interval: 1,202.86 – 1,225.17
8252 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,204.30 rating
Confidence interval: 1,198.38 – 1,210.22
45062 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,206.07 rating
Confidence interval: 1,199.76 – 1,212.38
37706 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,194.03 rating
Confidence interval: 1,188.73 – 1,199.33
56558 votes
- Category
- instruction_following
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,016.49 rating
Confidence interval: 1,000.54 – 1,032.43
3276 votes
- Category
- japanese
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,016.71 rating
Confidence interval: 999.48 – 1,033.94
5410 votes
- Category
- korean
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,173.74 rating
Confidence interval: 1,166.15 – 1,181.33
17500 votes
- Category
- longer_query
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,217.81 rating
Confidence interval: 1,210.37 – 1,225.26
20941 votes
- Category
- math
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,222.93 rating
Confidence interval: 1,215.56 – 1,230.30
21421 votes
- Category
- multi_turn
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,141.74 rating
Confidence interval: 1,136.64 – 1,146.83
66323 votes
- Category
- non_english
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,220.76 rating
Confidence interval: 1,217.18 – 1,224.34
156876 votes
- Category
- overall
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,196.36 rating
Confidence interval: 1,147.39 – 1,245.34
406 votes
- Category
- polish
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,158.68 rating
Confidence interval: 1,150.37 – 1,166.99
14995 votes
- Category
- russian
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
llama-3-70b-instruct
1,241.00 rating
Confidence interval: 1,221.29 – 1,260.72
2705 votes
- Category
- spanish
- Evaluated configuration
- llama-3-70b-instruct
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Llama 3 Community
0 selected Compare 0