BenchAtlas

Rankings / Microsoft

Phi 3 Small 8K Instruct

open weights

release date unknown

BenchAtlas Index

as of 2026-09-11
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
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1212.3
1200.71224.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1210.7
1202.81218.6
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1204.7
1193.11216.4
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1203.3
1189.81216.9
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1199.3
1179.71218.8
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1198.3
1188.31208.2
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1193.8
1175.41212.2
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1193.1
1180.41205.8
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
1192.0
1179.71204.2
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1188.2
1178.71197.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1170.5
1164.61176.4
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1167.8
1154.51181.1
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1166.2
1147.11185.3
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1162.2
1148.91175.5
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
1158.3
1144.51172.2
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1153.7
1144.91162.5
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1150.3
1136.01164.6
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1144.6
1120.21169.0
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
1140.1
1129.91150.3
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1132.8
1119.71146.0
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1119.5
1107.11131.7
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1118.7
1110.41126.9
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
1113.6
1101.01126.2
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1020.8
1010.31031.3
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
977.0
951.11003.0
communityLMArena Leaderboard Dataset