Phi 3 mini 128K instruct

Microsoft · microsoft/phi-3-mini-128k-instruct

ProviderMicrosoft
Familyphi
Typellm-code
Statusactive
Released2024-04-22

Reported benchmark scores

These scores carry one collection date for the whole card (2024-07) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
ARC-Challengeunassessed63.1
BIG-Bench Hardunassessed55.7
GPQA Diamondunassessed31.8
GSM8Kunassessed69.5
HellaSwagunassessed80.1
IFEvalunassessed59.8
MATH-500unassessed14.0
MMLU: Abstract Algebraunassessed38.0
MMLU: Anatomyunassessed65.2
MMLU: Astronomyunassessed78.9
MMLU: Business Ethicsunassessed68.0
MMLU: Clinical Knowledgeunassessed74.0
MMLU: College Biologyunassessed79.9
MMLU: College Chemistryunassessed44.0
MMLU: College Computer Scienceunassessed56.0
MMLU: College Mathematicsunassessed40.0
MMLU: College Medicineunassessed68.2
MMLU: College Physicsunassessed43.1
MMLU: Computer Securityunassessed76.0
MMLU: Conceptual Physicsunassessed69.8
MMLU: Econometricsunassessed49.1
MMLU: Electrical Engineeringunassessed62.1
MMLU: Elementary Mathematicsunassessed48.9
MMLU: Formal Logicunassessed57.1
MMLU: Global Factsunassessed37.0
MMLU: High School Biologyunassessed83.5
MMLU: High School Chemistryunassessed60.1
MMLU: High School Computer Scienceunassessed67.0
MMLU: High School European Historyunassessed81.2
MMLU: High School Geographyunassessed84.8
MMLU: High School Government and Politicsunassessed88.6
MMLU: High School Macroeconomicsunassessed73.3
MMLU: High School Mathematicsunassessed40.0
MMLU: High School Microeconomicsunassessed82.8
MMLU: High School Physicsunassessed44.4
MMLU: High School Psychologyunassessed89.0
MMLU: High School Statisticsunassessed64.8
MMLU: High School US Historyunassessed83.3
MMLU: High School World Historyunassessed79.7
MMLU: Human Agingunassessed70.9
MMLU: Human Sexualityunassessed75.6
MMLU: International Lawunassessed82.6
MMLU: Jurisprudenceunassessed77.8
MMLU: Logical Fallaciesunassessed81.6
MMLU: Machine Learningunassessed54.5
MMLU: Managementunassessed82.5
MMLU: Marketingunassessed88.9
MMLU: Medical Geneticsunassessed83.0
MMLU: Miscellaneousunassessed81.6
MMLU: Moral Disputesunassessed74.0
MMLU: Moral Scenariosunassessed58.4
MMLU: Nutritionunassessed77.8
MMLU: Philosophyunassessed73.6
MMLU: Prehistoryunassessed77.2
MMLU-Prounassessed37.3
MMLU: Professional Accountingunassessed58.5
MMLU: Professional Lawunassessed49.7
MMLU: Professional Medicineunassessed72.4
MMLU: Professional Psychologyunassessed75.3
MMLU: Public Relationsunassessed67.3
MMLU: Security Studiesunassessed74.7
MMLU: Sociologyunassessed85.6
MMLU: US Foreign Policyunassessed87.0
MMLU: Virologyunassessed47.0
MMLU: World Religionsunassessed80.7
MuSRunassessed39.4
TruthfulQAunassessed54.1
WinoGrandeunassessed72.8

Data

This card as JSON · Edit on GitHub