Phi-3 Mini 4K Instruct (June 2024)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsPhi-3 Mini 4K Instruct (June 2024)
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
Phi-3 Mini 4K Instruct (June 2024)
1,033.35 rating
Confidence interval: 1,015.54 – 1,051.17
1172 votes
- Category
- chinese
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,092.80 rating
Confidence interval: 1,079.07 – 1,106.53
1841 votes
- Category
- coding
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,044.34 rating
Confidence interval: 1,029.87 – 1,058.81
1955 votes
- Category
- creative_writing
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,128.77 rating
Confidence interval: 1,120.56 – 1,136.97
6694 votes
- Category
- english
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
873.97 rating
Confidence interval: 861.87 – 886.08
8201 votes
- Category
- exclude_ties
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,050.68 rating
Confidence interval: 1,024.72 – 1,076.64
486 votes
- Category
- expert
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,030.83 rating
Confidence interval: 998.56 – 1,063.10
397 votes
- Category
- german
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,087.32 rating
Confidence interval: 1,076.57 – 1,098.06
3155 votes
- Category
- hard_prompts
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,114.48 rating
Confidence interval: 1,101.59 – 1,127.37
2028 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,022.84 rating
Confidence interval: 1,006.04 – 1,039.64
1424 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,031.26 rating
Confidence interval: 1,017.49 – 1,045.02
1973 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,068.49 rating
Confidence interval: 1,043.77 – 1,093.20
706 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,068.01 rating
Confidence interval: 1,053.45 – 1,082.56
1956 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,146.95 rating
Confidence interval: 1,132.34 – 1,161.56
1357 votes
- Category
- industry_mathematical
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,042.21 rating
Confidence interval: 1,016.74 – 1,067.68
653 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,087.96 rating
Confidence interval: 1,076.67 – 1,099.25
3104 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,056.61 rating
Confidence interval: 1,045.40 – 1,067.81
3382 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,057.59 rating
Confidence interval: 1,048.00 – 1,067.18
4431 votes
- Category
- instruction_following
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
954.53 rating
Confidence interval: 921.81 – 987.25
354 votes
- Category
- japanese
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
879.74 rating
Confidence interval: 838.98 – 920.50
292 votes
- Category
- korean
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,041.22 rating
Confidence interval: 1,022.60 – 1,059.85
1035 votes
- Category
- longer_query
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,151.98 rating
Confidence interval: 1,138.37 – 1,165.59
1568 votes
- Category
- math
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,049.09 rating
Confidence interval: 1,034.43 – 1,063.74
1839 votes
- Category
- multi_turn
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,012.50 rating
Confidence interval: 1,003.27 – 1,021.72
5603 votes
- Category
- non_english
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,079.93 rating
Confidence interval: 1,073.59 – 1,086.27
12297 votes
- Category
- overall
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Phi-3 Mini 4K Instruct (June 2024)
1,018.94 rating
Confidence interval: 1,002.25 – 1,035.64
1415 votes
- Category
- russian
- Evaluated configuration
- Phi-3 Mini 4K Instruct (June 2024)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0