Qwen1.5-72B-Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen1.5-72B-Chat
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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
Qwen1.5-72B-Chat
1,186.11 rating
Confidence interval: 1,173.82 – 1,198.40
4167 votes
- Category
- chinese
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,165.15 rating
Confidence interval: 1,155.62 – 1,174.67
6370 votes
- Category
- coding
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,136.76 rating
Confidence interval: 1,126.77 – 1,146.75
5888 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,186.51 rating
Confidence interval: 1,180.29 – 1,192.73
25039 votes
- Category
- english
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,032.19 rating
Confidence interval: 1,024.36 – 1,040.03
25865 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,135.78 rating
Confidence interval: 1,120.61 – 1,150.95
1846 votes
- Category
- expert
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,159.24 rating
Confidence interval: 1,134.02 – 1,184.45
858 votes
- Category
- french
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,083.71 rating
Confidence interval: 1,063.61 – 1,103.81
1091 votes
- Category
- german
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,147.75 rating
Confidence interval: 1,139.98 – 1,155.52
10854 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,162.21 rating
Confidence interval: 1,153.33 – 1,171.09
7597 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,116.92 rating
Confidence interval: 1,105.35 – 1,128.48
3842 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,125.35 rating
Confidence interval: 1,115.40 – 1,135.30
5818 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,173.48 rating
Confidence interval: 1,158.45 – 1,188.51
2091 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,157.73 rating
Confidence interval: 1,147.90 – 1,167.57
6892 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,171.84 rating
Confidence interval: 1,161.53 – 1,182.15
4522 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,136.26 rating
Confidence interval: 1,121.58 – 1,150.93
2386 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,160.72 rating
Confidence interval: 1,152.53 – 1,168.91
10756 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,159.07 rating
Confidence interval: 1,150.60 – 1,167.54
9492 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,141.20 rating
Confidence interval: 1,133.90 – 1,148.50
13814 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,061.39 rating
Confidence interval: 1,033.30 – 1,089.47
495 votes
- Category
- japanese
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,049.46 rating
Confidence interval: 1,021.36 – 1,077.56
552 votes
- Category
- korean
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,156.70 rating
Confidence interval: 1,145.22 – 1,168.17
3483 votes
- Category
- longer_query
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,163.69 rating
Confidence interval: 1,154.02 – 1,173.36
5327 votes
- Category
- math
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,159.91 rating
Confidence interval: 1,149.63 – 1,170.19
5502 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,134.88 rating
Confidence interval: 1,127.48 – 1,142.28
14263 votes
- Category
- non_english
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,166.13 rating
Confidence interval: 1,160.95 – 1,171.31
39302 votes
- Category
- overall
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,103.92 rating
Confidence interval: 1,091.15 – 1,116.69
2666 votes
- Category
- russian
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen1.5-72B-Chat
1,110.21 rating
Confidence interval: 1,080.32 – 1,140.10
501 votes
- Category
- spanish
- Evaluated configuration
- Qwen1.5-72B-Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Qianwen LICENSE
0 selected Compare 0