BenchAtlas

Rankings / Microsoft

Phi 3 Mini 4K Instruct

open weights

release date unknown

BenchAtlas Index

as of 2026-07-14
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

25 results
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1186.6
1174.91198.3
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1177.3
1165.71189.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1171.6
1163.51179.8
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1162.5
1152.61172.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1154.3
1141.31167.2
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1153.4
1134.11172.8
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1152.0
1142.41161.7
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1149.9
1137.61162.1
communityLMArena Leaderboard Dataset
Industry Life And Physical And Social Science (style control)older version
arena=text · category=industry_life_and_physical_and_social_science · style_control=true
1145.4
1132.71158.1
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1137.2
1117.61156.8
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1128.6
1108.01149.2
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1127.5
1121.11133.9
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1112.3
1103.41121.1
communityLMArena Leaderboard Dataset
Industry Business And Management And Financial Operations (style control)older version
arena=text · category=industry_business_and_management_and_financial_operations · style_control=true
1111.5
1097.81125.2
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1111.1
1096.41125.7
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1108.0
1084.01132.0
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1106.8
1091.51122.2
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1092.2
1081.61102.7
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1073.9
1065.51082.3
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1073.1
1060.21086.1
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1068.5
1056.11080.9
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1066.4
1053.21079.6
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1063.5
1050.01077.0
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
967.8
942.8992.7
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
949.0
937.5960.5
communityLMArena Leaderboard Dataset