GeekRadar / The comparison desk
COMPARE.
AI models
Not reported

Zephyr ORPO 141B A35B v0.1

Model evaluation

Capability & preference

Human preference · Arena

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

Zephyr ORPO 141B A35B v0.1 1143.7 Zephyr ORPO 141B A35B v0.1 · 95% interval 1133.0–1154.4 · 4,652 votes · 2026-11-08

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 · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,082.10 rating

Confidence interval: 1,058.96 – 1,105.25

657 votes

Category
chinese
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,129.06 rating

Confidence interval: 1,108.67 – 1,149.45

831 votes

Category
coding
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,112.98 rating

Confidence interval: 1,089.93 – 1,136.03

635 votes

Category
creative_writing
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,174.40 rating

Confidence interval: 1,161.25 – 1,187.54

2702 votes

Category
english
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

998.34 rating

Confidence interval: 982.75 – 1,013.93

3178 votes

Category
exclude_ties
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,061.41 rating

Confidence interval: 1,021.61 – 1,101.20

219 votes

Category
expert
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,115.63 rating

Confidence interval: 1,099.06 – 1,132.20

1240 votes

Category
hard_prompts
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,132.93 rating

Confidence interval: 1,112.73 – 1,153.13

820 votes

Category
hard_prompts_english
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,088.87 rating

Confidence interval: 1,061.22 – 1,116.51

441 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,128.10 rating

Confidence interval: 1,105.29 – 1,150.91

617 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,135.44 rating

Confidence interval: 1,098.17 – 1,172.71

240 votes

Category
industry_legal_and_government
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,142.21 rating

Confidence interval: 1,121.41 – 1,163.02

827 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,144.76 rating

Confidence interval: 1,120.95 – 1,168.57

526 votes

Category
industry_mathematical
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,106.33 rating

Confidence interval: 1,071.08 – 1,141.59

284 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,133.58 rating

Confidence interval: 1,116.95 – 1,150.21

1344 votes

Category
industry_software_and_it_services
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,139.05 rating

Confidence interval: 1,121.24 – 1,156.86

1129 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,117.55 rating

Confidence interval: 1,102.17 – 1,132.94

1593 votes

Category
instruction_following
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,104.58 rating

Confidence interval: 1,076.80 – 1,132.35

448 votes

Category
longer_query
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,147.81 rating

Confidence interval: 1,125.67 – 1,169.94

589 votes

Category
math
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,099.50 rating

Confidence interval: 1,075.46 – 1,123.54

683 votes

Category
multi_turn
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,098.09 rating

Confidence interval: 1,084.02 – 1,112.16

1950 votes

Category
non_english
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,143.71 rating

Confidence interval: 1,133.00 – 1,154.42

4652 votes

Category
overall
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-08 · rating

Zephyr ORPO 141B A35B v0.1

1,115.72 rating

Confidence interval: 1,088.49 – 1,142.95

407 votes

Category
russian
Evaluated configuration
Zephyr ORPO 141B A35B v0.1
Evaluation type
human preference

Run it locally

Inference · memory estimate

Zephyr ORPO 141B A35B v0.1

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0