GeekRadar / The comparison desk

COMPARE.

AI models

microsoft

WizardLM 13B

Model evaluation

Capability & preference

Human preference · Arena

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

WizardLM 13B 1076.5 WizardLM 13B · 95% interval 1067.3–1085.7 · 7,044 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

WizardLM 13B

1,022.68 rating

Confidence interval: 990.03 – 1,055.34

287 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,034.59 rating

Confidence interval: 1,012.82 – 1,056.37

735 votes

Oct 28, 2026

Category: coding
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,090.15 rating

Confidence interval: 1,072.35 – 1,107.95

1375 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,101.70 rating

Confidence interval: 1,091.32 – 1,112.08

5508 votes

Oct 28, 2026

Category: english
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

904.03 rating

Confidence interval: 890.79 – 917.27

4797 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,017.53 rating

Confidence interval: 1,001.22 – 1,033.84

1278 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,033.74 rating

Confidence interval: 1,015.60 – 1,051.87

1066 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,006.31 rating

Confidence interval: 982.06 – 1,030.56

634 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,074.75 rating

Confidence interval: 1,056.40 – 1,093.11

1219 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,099.83 rating

Confidence interval: 1,067.69 – 1,131.98

365 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,068.81 rating

Confidence interval: 1,050.71 – 1,086.91

1246 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,015.11 rating

Confidence interval: 991.95 – 1,038.28

567 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,064.79 rating

Confidence interval: 1,029.74 – 1,099.83

323 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,052.16 rating

Confidence interval: 1,036.38 – 1,067.94

1618 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,098.16 rating

Confidence interval: 1,082.84 – 1,113.47

1814 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,048.28 rating

Confidence interval: 1,034.44 – 1,062.13

2003 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,053.27 rating

Confidence interval: 1,013.50 – 1,093.03

203 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,017.08 rating

Confidence interval: 996.56 – 1,037.59

669 votes

Oct 28, 2026

Category: math
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,047.03 rating

Confidence interval: 1,027.06 – 1,066.99

983 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,034.21 rating

Confidence interval: 1,018.87 – 1,049.55

1536 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

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

WizardLM 13B

1,076.51 rating

Confidence interval: 1,067.29 – 1,085.73

7044 votes

Oct 28, 2026

Category: overall
Evaluated configuration: WizardLM 13B
Evaluation type: human preference

Run it locally

Inference · memory estimate

WizardLM 13B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Llama 2 Community