Qwen1.5-4B-Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen1.5-4B-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
Qwen1.5-4B-Chat
1,023.81 rating
Confidence interval: 1,003.94 – 1,043.68
1028 votes
- Category
- chinese
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
998.53 rating
Confidence interval: 981.37 – 1,015.69
1283 votes
- Category
- coding
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
968.94 rating
Confidence interval: 950.22 – 987.67
1080 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
1,015.10 rating
Confidence interval: 1,004.29 – 1,025.91
4756 votes
- Category
- english
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
763.04 rating
Confidence interval: 747.37 – 778.71
5172 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
979.79 rating
Confidence interval: 948.62 – 1,010.96
356 votes
- Category
- expert
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
901.93 rating
Confidence interval: 861.87 – 941.99
211 votes
- Category
- german
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
976.08 rating
Confidence interval: 962.22 – 989.94
2075 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
983.33 rating
Confidence interval: 967.39 – 999.27
1419 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
964.80 rating
Confidence interval: 941.48 – 988.12
738 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
952.57 rating
Confidence interval: 934.50 – 970.65
1147 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
1,010.31 rating
Confidence interval: 978.39 – 1,042.23
390 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
976.23 rating
Confidence interval: 957.89 – 994.56
1277 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
998.28 rating
Confidence interval: 978.37 – 1,018.18
820 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
955.41 rating
Confidence interval: 924.52 – 986.31
433 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
994.46 rating
Confidence interval: 980.11 – 1,008.82
2193 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
1,000.78 rating
Confidence interval: 986.00 – 1,015.55
1895 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
978.32 rating
Confidence interval: 965.51 – 991.14
2636 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
987.39 rating
Confidence interval: 963.91 – 1,010.86
692 votes
- Category
- longer_query
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
1,025.88 rating
Confidence interval: 1,008.27 – 1,043.50
988 votes
- Category
- math
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
977.46 rating
Confidence interval: 958.73 – 996.19
1136 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
979.19 rating
Confidence interval: 966.43 – 991.95
2841 votes
- Category
- non_english
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
997.21 rating
Confidence interval: 987.99 – 1,006.42
7597 votes
- Category
- overall
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen1.5-4B-Chat
951.82 rating
Confidence interval: 927.14 – 976.50
564 votes
- Category
- russian
- Evaluated configuration
- Qwen1.5-4B-Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Qianwen LICENSE
0 selected Compare 0