qwen2-72b-instruct
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsqwen2-72b-instruct
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 · 2026-10-15 · rating
qwen2-72b-instruct
1,239.90 rating
Confidence interval: 1,228.33 – 1,251.47
4078 votes
- Category
- chinese
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,195.64 rating
Confidence interval: 1,186.76 – 1,204.53
6249 votes
- Category
- coding
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,180.75 rating
Confidence interval: 1,171.27 – 1,190.23
5504 votes
- Category
- creative_writing
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,222.02 rating
Confidence interval: 1,216.01 – 1,228.03
19928 votes
- Category
- english
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,087.16 rating
Confidence interval: 1,079.84 – 1,094.49
23757 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,171.01 rating
Confidence interval: 1,156.37 – 1,185.65
1763 votes
- Category
- expert
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,170.40 rating
Confidence interval: 1,143.77 – 1,197.03
596 votes
- Category
- french
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,150.79 rating
Confidence interval: 1,132.83 – 1,168.74
1340 votes
- Category
- german
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,190.46 rating
Confidence interval: 1,183.19 – 1,197.73
10780 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,205.64 rating
Confidence interval: 1,196.96 – 1,214.32
6483 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,146.35 rating
Confidence interval: 1,135.68 – 1,157.03
4345 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,165.60 rating
Confidence interval: 1,156.47 – 1,174.73
5791 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,192.92 rating
Confidence interval: 1,178.95 – 1,206.88
2262 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,195.17 rating
Confidence interval: 1,185.82 – 1,204.52
6456 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,230.63 rating
Confidence interval: 1,220.67 – 1,240.60
4235 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,175.58 rating
Confidence interval: 1,161.02 – 1,190.15
2067 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,192.93 rating
Confidence interval: 1,185.37 – 1,200.49
10308 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,201.67 rating
Confidence interval: 1,193.86 – 1,209.48
9976 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,181.01 rating
Confidence interval: 1,174.25 – 1,187.77
14194 votes
- Category
- instruction_following
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,110.89 rating
Confidence interval: 1,089.63 – 1,132.14
901 votes
- Category
- japanese
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,082.70 rating
Confidence interval: 1,060.95 – 1,104.45
1167 votes
- Category
- korean
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,192.09 rating
Confidence interval: 1,181.95 – 1,202.22
4614 votes
- Category
- longer_query
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,234.75 rating
Confidence interval: 1,225.34 – 1,244.15
4835 votes
- Category
- math
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,195.48 rating
Confidence interval: 1,186.30 – 1,204.67
6698 votes
- Category
- multi_turn
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,175.87 rating
Confidence interval: 1,169.48 – 1,182.25
17397 votes
- Category
- non_english
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,203.23 rating
Confidence interval: 1,198.33 – 1,208.14
37325 votes
- Category
- overall
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,168.74 rating
Confidence interval: 1,158.34 – 1,179.14
4555 votes
- Category
- russian
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
qwen2-72b-instruct
1,168.78 rating
Confidence interval: 1,141.05 – 1,196.51
596 votes
- Category
- spanish
- Evaluated configuration
- qwen2-72b-instruct
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Qianwen LICENSE
0 selected Compare 0