GeekRadar / The comparison desk

COMPARE.

AI models

Llama-2-13b-chat

AI model

Open weights: Yes

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Llama-2-13b-chat 1084.4 Llama 2 13B Chat · 95% interval 1077.8–1091.1 · 19,174 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.

Test version

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

Llama-2-13b-chat

1,000.96 rating

Confidence interval: 982.16 – 1,019.75

1161 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,062.04 rating

Confidence interval: 1,049.26 – 1,074.81

2626 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,046.57 rating

Confidence interval: 1,034.10 – 1,059.04

3296 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,119.87 rating

Confidence interval: 1,112.18 – 1,127.57

13860 votes

Oct 28, 2026

Category: english
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

908.38 rating

Confidence interval: 898.50 – 918.25

12677 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,029.76 rating

Confidence interval: 1,004.57 – 1,054.96

539 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,044.46 rating

Confidence interval: 1,004.63 – 1,084.29

262 votes

Oct 28, 2026

Category: french
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,009.05 rating

Confidence interval: 978.90 – 1,039.20

454 votes

Oct 28, 2026

Category: german
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,050.80 rating

Confidence interval: 1,040.60 – 1,061.01

4475 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,072.65 rating

Confidence interval: 1,060.83 – 1,084.47

3347 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,055.57 rating

Confidence interval: 1,039.57 – 1,071.57

1709 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,047.39 rating

Confidence interval: 1,034.97 – 1,059.80

3085 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,079.90 rating

Confidence interval: 1,059.06 – 1,100.73

1004 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,081.79 rating

Confidence interval: 1,069.00 – 1,094.59

3270 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,068.83 rating

Confidence interval: 1,054.73 – 1,082.94

1977 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,071.55 rating

Confidence interval: 1,050.71 – 1,092.39

970 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,072.59 rating

Confidence interval: 1,062.36 – 1,082.83

4910 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,061.44 rating

Confidence interval: 1,050.79 – 1,072.09

4785 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,045.18 rating

Confidence interval: 1,035.91 – 1,054.44

6097 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

894.05 rating

Confidence interval: 844.62 – 943.47

175 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

953.30 rating

Confidence interval: 902.92 – 1,003.69

172 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,063.90 rating

Confidence interval: 1,046.67 – 1,081.12

1193 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,064.87 rating

Confidence interval: 1,051.47 – 1,078.28

2218 votes

Oct 28, 2026

Category: math
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,050.12 rating

Confidence interval: 1,036.28 – 1,063.95

2596 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,023.83 rating

Confidence interval: 1,014.17 – 1,033.49

5314 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,084.43 rating

Confidence interval: 1,077.78 – 1,091.08

19174 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,054.32 rating

Confidence interval: 1,033.57 – 1,075.07

783 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

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

Llama-2-13b-chat

1,086.51 rating

Confidence interval: 1,047.05 – 1,125.97

262 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Llama 2 13B Chat
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,001.01 rating

Confidence interval: 982.21 – 1,019.80

1161 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,062.14 rating

Confidence interval: 1,049.36 – 1,074.91

2626 votes

Oct 15, 2026

Category: coding
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,046.72 rating

Confidence interval: 1,034.25 – 1,059.20

3296 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,119.82 rating

Confidence interval: 1,112.13 – 1,127.52

13860 votes

Oct 15, 2026

Category: english
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Llama-2-13b-chat

908.39 rating

Confidence interval: 898.51 – 918.26

12677 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,029.80 rating

Confidence interval: 1,004.60 – 1,055.01

539 votes

Oct 15, 2026

Category: expert
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,044.14 rating

Confidence interval: 1,004.29 – 1,084.00

262 votes

Oct 15, 2026

Category: french
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,009.04 rating

Confidence interval: 978.93 – 1,039.16

454 votes

Oct 15, 2026

Category: german
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,050.79 rating

Confidence interval: 1,040.58 – 1,061.00

4475 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,072.54 rating

Confidence interval: 1,060.72 – 1,084.36

3347 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,055.61 rating

Confidence interval: 1,039.61 – 1,071.61

1709 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,047.45 rating

Confidence interval: 1,035.03 – 1,059.86

3085 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,079.64 rating

Confidence interval: 1,058.80 – 1,100.48

1004 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,081.77 rating

Confidence interval: 1,068.97 – 1,094.57

3270 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,068.83 rating

Confidence interval: 1,054.72 – 1,082.93

1977 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,071.60 rating

Confidence interval: 1,050.76 – 1,092.45

970 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,072.68 rating

Confidence interval: 1,062.44 – 1,082.91

4910 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,061.50 rating

Confidence interval: 1,050.85 – 1,072.16

4785 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,045.19 rating

Confidence interval: 1,035.92 – 1,054.46

6097 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Llama-2-13b-chat

893.88 rating

Confidence interval: 844.47 – 943.29

175 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

953.34 rating

Confidence interval: 902.96 – 1,003.73

172 votes

Oct 15, 2026

Category: korean
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,063.94 rating

Confidence interval: 1,046.71 – 1,081.17

1193 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,064.83 rating

Confidence interval: 1,051.43 – 1,078.24

2218 votes

Oct 15, 2026

Category: math
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,050.11 rating

Confidence interval: 1,036.27 – 1,063.95

2596 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,023.92 rating

Confidence interval: 1,014.26 – 1,033.58

5314 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,084.42 rating

Confidence interval: 1,077.76 – 1,091.07

19174 votes

Oct 15, 2026

Category: overall
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,054.47 rating

Confidence interval: 1,033.71 – 1,075.23

783 votes

Oct 15, 2026

Category: russian
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

Llama-2-13b-chat

1,086.43 rating

Confidence interval: 1,046.93 – 1,125.92

262 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: llama-2-13b-chat
Evaluation type: human preference

Run it locally

Inference · memory estimate

Llama-2-13b-chat

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Open weights: Yes
Model license: llama2

Input modalities

text

Output modalities

text