GeekRadar / The comparison desk
COMPARE.
AI models
Not reported

Vicuna 13B

Model evaluation

Capability & preference

Human preference · Arena

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

Vicuna 13B 1057.6 Vicuna 13B · 95% interval 1051.1–1064.2 · 19,367 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

Vicuna 13B

1,039.46 rating

Confidence interval: 1,020.14 – 1,058.77

1178 votes

Category
chinese
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Vicuna 13B

1,040.37 rating

Confidence interval: 1,026.74 – 1,053.99

2389 votes

Category
coding
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Vicuna 13B

1,057.81 rating

Confidence interval: 1,045.23 – 1,070.39

3346 votes

Category
creative_writing
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Vicuna 13B

1,080.53 rating

Confidence interval: 1,073.07 – 1,087.99

14788 votes

Category
english
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Vicuna 13B

868.17 rating

Confidence interval: 858.31 – 878.02

13246 votes

Category
exclude_ties
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Vicuna 13B

993.85 rating

Confidence interval: 962.74 – 1,024.96

321 votes

Category
expert
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Vicuna 13B

1,020.45 rating

Confidence interval: 975.19 – 1,065.70

198 votes

Category
french
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Vicuna 13B

992.35 rating

Confidence interval: 955.93 – 1,028.77

283 votes

Category
german
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Vicuna 13B

1,023.45 rating

Confidence interval: 1,012.96 – 1,033.94

3971 votes

Category
hard_prompts
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Vicuna 13B

1,035.60 rating

Confidence interval: 1,023.74 – 1,047.46

3220 votes

Category
hard_prompts_english
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Vicuna 13B

1,005.91 rating

Confidence interval: 988.90 – 1,022.92

1638 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Vicuna 13B

1,030.80 rating

Confidence interval: 1,018.40 – 1,043.20

3239 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Vicuna 13B

1,057.04 rating

Confidence interval: 1,035.09 – 1,078.99

899 votes

Category
industry_legal_and_government
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Vicuna 13B

1,034.43 rating

Confidence interval: 1,021.62 – 1,047.25

3288 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Vicuna 13B

1,021.78 rating

Confidence interval: 1,006.77 – 1,036.79

1884 votes

Category
industry_mathematical
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Vicuna 13B

1,019.03 rating

Confidence interval: 996.91 – 1,041.14

884 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Vicuna 13B

1,047.72 rating

Confidence interval: 1,037.12 – 1,058.33

4692 votes

Category
industry_software_and_it_services
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Vicuna 13B

1,078.83 rating

Confidence interval: 1,068.20 – 1,089.46

4672 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Vicuna 13B

1,034.95 rating

Confidence interval: 1,025.50 – 1,044.40

5665 votes

Category
instruction_following
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Vicuna 13B

918.48 rating

Confidence interval: 866.47 – 970.49

125 votes

Category
japanese
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Vicuna 13B

1,047.04 rating

Confidence interval: 1,025.84 – 1,068.24

756 votes

Category
longer_query
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Vicuna 13B

1,030.37 rating

Confidence interval: 1,016.68 – 1,044.06

2146 votes

Category
math
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Vicuna 13B

1,030.83 rating

Confidence interval: 1,016.90 – 1,044.77

2552 votes

Category
multi_turn
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Vicuna 13B

1,027.07 rating

Confidence interval: 1,016.98 – 1,037.16

4579 votes

Category
non_english
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Vicuna 13B

1,057.63 rating

Confidence interval: 1,051.05 – 1,064.21

19367 votes

Category
overall
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Vicuna 13B

1,041.97 rating

Confidence interval: 1,014.99 – 1,068.95

448 votes

Category
russian
Evaluated configuration
Vicuna 13B
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Vicuna 13B

1,076.57 rating

Confidence interval: 1,027.92 – 1,125.21

161 votes

Category
spanish
Evaluated configuration
Vicuna 13B
Evaluation type
human preference

Run it locally

Inference · memory estimate

Vicuna 13B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Llama 2 Community