GeekRadar / The comparison desk

COMPARE.

AI models

microsoft

wizardlm-70b

Model evaluation

Capability & preference

Human preference · Arena

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

wizardlm-70b 1119.5 wizardlm-70b · 95% interval 1110.2–1128.8 · 8,214 votes · 2026-10-15

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

wizardlm-70b

1,052.40 rating

Confidence interval: 1,020.18 – 1,084.62

334 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,080.97 rating

Confidence interval: 1,061.36 – 1,100.57

988 votes

Oct 15, 2026

Category: coding
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,149.04 rating

Confidence interval: 1,132.32 – 1,165.76

1779 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,150.31 rating

Confidence interval: 1,140.12 – 1,160.51

6411 votes

Oct 15, 2026

Category: english
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

966.31 rating

Confidence interval: 953.31 – 979.31

5678 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,082.64 rating

Confidence interval: 1,038.14 – 1,127.14

193 votes

Oct 15, 2026

Category: german
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,079.02 rating

Confidence interval: 1,063.91 – 1,094.12

1752 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,095.96 rating

Confidence interval: 1,079.68 – 1,112.24

1475 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,078.45 rating

Confidence interval: 1,054.75 – 1,102.15

682 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,112.29 rating

Confidence interval: 1,095.00 – 1,129.58

1539 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,129.01 rating

Confidence interval: 1,099.88 – 1,158.15

434 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,109.31 rating

Confidence interval: 1,091.49 – 1,127.14

1334 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,107.35 rating

Confidence interval: 1,086.82 – 1,127.89

764 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,094.65 rating

Confidence interval: 1,064.04 – 1,125.26

385 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,088.43 rating

Confidence interval: 1,073.27 – 1,103.58

1935 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,144.57 rating

Confidence interval: 1,129.90 – 1,159.24

2313 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,092.92 rating

Confidence interval: 1,079.63 – 1,106.20

2680 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,096.81 rating

Confidence interval: 1,065.57 – 1,128.05

355 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,115.94 rating

Confidence interval: 1,096.86 – 1,135.03

903 votes

Oct 15, 2026

Category: math
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,108.32 rating

Confidence interval: 1,088.97 – 1,127.66

1178 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,077.47 rating

Confidence interval: 1,061.87 – 1,093.07

1803 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,119.48 rating

Confidence interval: 1,110.15 – 1,128.81

8214 votes

Oct 15, 2026

Category: overall
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

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

wizardlm-70b

1,155.29 rating

Confidence interval: 1,110.61 – 1,199.98

172 votes

Oct 15, 2026

Category: russian
Evaluated configuration: wizardlm-70b
Evaluation type: human preference

Run it locally

Inference · memory estimate

wizardlm-70b

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Llama 2 Community