GeekRadar / The comparison desk

COMPARE.

AI models

Llama 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.

Llama 3 8B Instruct 1165.6 Llama 3 8B Instruct · 95% interval 1161.9–1169.3 · 104,642 votes · 2026-10-28

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 8B Instruct

1,076.00 rating

Confidence interval: 1,066.22 – 1,085.77

10757 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,151.31 rating

Confidence interval: 1,143.80 – 1,158.83

18374 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,149.50 rating

Confidence interval: 1,141.41 – 1,157.60

15365 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,213.22 rating

Confidence interval: 1,208.35 – 1,218.08

61703 votes

Oct 28, 2026

Category: english
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,029.96 rating

Confidence interval: 1,023.99 – 1,035.94

67687 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,113.04 rating

Confidence interval: 1,101.33 – 1,124.74

5360 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,159.13 rating

Confidence interval: 1,137.37 – 1,180.90

1624 votes

Oct 28, 2026

Category: french
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,104.42 rating

Confidence interval: 1,089.54 – 1,119.31

3370 votes

Oct 28, 2026

Category: german
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,133.13 rating

Confidence interval: 1,127.06 – 1,139.20

30221 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,163.63 rating

Confidence interval: 1,156.46 – 1,170.81

19891 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Llama 3 8B Instruct

1,127.07 rating

Confidence interval: 1,118.06 – 1,136.08

10764 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Llama 3 8B Instruct

1,131.94 rating

Confidence interval: 1,124.18 – 1,139.69

15413 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Llama 3 8B Instruct

1,167.76 rating

Confidence interval: 1,156.14 – 1,179.39

5578 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Llama 3 8B Instruct

1,170.04 rating

Confidence interval: 1,162.15 – 1,177.93

17322 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,153.29 rating

Confidence interval: 1,145.06 – 1,161.53

12836 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,147.94 rating

Confidence interval: 1,135.80 – 1,160.08

5400 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,155.96 rating

Confidence interval: 1,149.49 – 1,162.44

29645 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Llama 3 8B Instruct

1,147.73 rating

Confidence interval: 1,141.09 – 1,154.37

25481 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,127.03 rating

Confidence interval: 1,121.38 – 1,132.68

37733 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

967.57 rating

Confidence interval: 949.30 – 985.84

1992 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,003.53 rating

Confidence interval: 984.29 – 1,022.78

2422 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,127.39 rating

Confidence interval: 1,118.84 – 1,135.95

11165 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,151.20 rating

Confidence interval: 1,143.35 – 1,159.05

14252 votes

Oct 28, 2026

Category: math
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,152.45 rating

Confidence interval: 1,144.36 – 1,160.54

14815 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,097.45 rating

Confidence interval: 1,092.10 – 1,102.80

42939 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,165.58 rating

Confidence interval: 1,161.86 – 1,169.29

104642 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,136.89 rating

Confidence interval: 1,083.94 – 1,189.83

257 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,109.09 rating

Confidence interval: 1,100.09 – 1,118.09

10009 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Llama 3 8B Instruct

1,172.82 rating

Confidence interval: 1,151.65 – 1,193.98

1744 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Llama 3 8B Instruct
Evaluation type: human preference

Run it locally

Inference · memory estimate

Llama 3 8B Instruct

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Llama 3 Community