Qwen-14B-Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen-14B-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
Qwen-14B-Chat
1,076.84 rating
Confidence interval: 1,033.58 – 1,120.09
195 votes
- Category
- chinese
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,071.25 rating
Confidence interval: 1,047.66 – 1,094.84
599 votes
- Category
- coding
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,027.38 rating
Confidence interval: 1,006.70 – 1,048.06
898 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,068.48 rating
Confidence interval: 1,056.63 – 1,080.33
3849 votes
- Category
- english
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen-14B-Chat
865.15 rating
Confidence interval: 849.56 – 880.74
3347 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,026.95 rating
Confidence interval: 1,008.19 – 1,045.71
1006 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,040.96 rating
Confidence interval: 1,020.68 – 1,061.23
830 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,001.43 rating
Confidence interval: 972.99 – 1,029.88
426 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen-14B-Chat
996.45 rating
Confidence interval: 975.31 – 1,017.58
847 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,050.73 rating
Confidence interval: 1,013.09 – 1,088.37
274 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,010.15 rating
Confidence interval: 988.79 – 1,031.52
894 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,073.16 rating
Confidence interval: 1,047.46 – 1,098.86
467 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,009.00 rating
Confidence interval: 970.81 – 1,047.20
268 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,052.72 rating
Confidence interval: 1,034.50 – 1,070.95
1173 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,049.84 rating
Confidence interval: 1,031.78 – 1,067.90
1230 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,031.16 rating
Confidence interval: 1,014.81 – 1,047.51
1470 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,028.20 rating
Confidence interval: 990.28 – 1,066.13
214 votes
- Category
- longer_query
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,067.70 rating
Confidence interval: 1,044.11 – 1,091.29
534 votes
- Category
- math
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,022.07 rating
Confidence interval: 998.77 – 1,045.38
753 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,041.36 rating
Confidence interval: 1,022.51 – 1,060.22
1115 votes
- Category
- non_english
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen-14B-Chat
1,051.00 rating
Confidence interval: 1,040.14 – 1,061.86
4964 votes
- Category
- overall
- Evaluated configuration
- Qwen-14B-Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Qianwen LICENSE
0 selected Compare 0