Meta Llama 3 8B Instruct

Meta · meta/meta-llama-3-8b-instruct

ProviderMeta
Familyllama
Typellm-chat
Statusactive
Released2024-04-17

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-Challengeunassessed60.8
BIG-Bench Hardunassessed49.1
GPQA Diamondunassessed29.3
GSM8Kunassessed68.7
HellaSwagunassessed78.6
IFEvalunassessed47.8
MATH-500unassessed9.1
MMLU: Abstract Algebraunassessed32.0
MMLU: Anatomyunassessed65.2
MMLU: Astronomyunassessed70.4
MMLU: Business Ethicsunassessed69.0
MMLU: Clinical Knowledgeunassessed74.7
MMLU: College Biologyunassessed79.9
MMLU: College Chemistryunassessed47.0
MMLU: College Computer Scienceunassessed59.0
MMLU: College Mathematicsunassessed39.0
MMLU: College Medicineunassessed63.6
MMLU: College Physicsunassessed50.0
MMLU: Computer Securityunassessed77.0
MMLU: Conceptual Physicsunassessed60.4
MMLU: Econometricsunassessed60.5
MMLU: Electrical Engineeringunassessed62.8
MMLU: Elementary Mathematicsunassessed44.4
MMLU: Formal Logicunassessed48.4
MMLU: Global Factsunassessed40.0
MMLU: High School Biologyunassessed78.4
MMLU: High School Chemistryunassessed50.7
MMLU: High School Computer Scienceunassessed75.0
MMLU: High School European Historyunassessed74.5
MMLU: High School Geographyunassessed84.3
MMLU: High School Government and Politicsunassessed91.2
MMLU: High School Macroeconomicsunassessed65.9
MMLU: High School Mathematicsunassessed40.0
MMLU: High School Microeconomicsunassessed76.5
MMLU: High School Physicsunassessed44.4
MMLU: High School Psychologyunassessed83.7
MMLU: High School Statisticsunassessed53.7
MMLU: High School US Historyunassessed85.8
MMLU: High School World Historyunassessed84.4
MMLU: Human Agingunassessed72.2
MMLU: Human Sexualityunassessed77.9
MMLU: International Lawunassessed81.8
MMLU: Jurisprudenceunassessed77.8
MMLU: Logical Fallaciesunassessed76.7
MMLU: Machine Learningunassessed54.5
MMLU: Managementunassessed78.6
MMLU: Marketingunassessed90.6
MMLU: Medical Geneticsunassessed80.0
MMLU: Miscellaneousunassessed79.8
MMLU: Moral Disputesunassessed74.9
MMLU: Moral Scenariosunassessed43.7
MMLU: Nutritionunassessed74.5
MMLU: Philosophyunassessed71.4
MMLU: Prehistoryunassessed74.1
MMLU-Prounassessed35.9
MMLU: Professional Accountingunassessed52.8
MMLU: Professional Lawunassessed47.8
MMLU: Professional Medicineunassessed71.7
MMLU: Professional Psychologyunassessed70.6
MMLU: Public Relationsunassessed64.5
MMLU: Security Studiesunassessed73.9
MMLU: Sociologyunassessed86.6
MMLU: US Foreign Policyunassessed86.0
MMLU: Virologyunassessed51.2
MMLU: World Religionsunassessed77.8
MuSRunassessed38.1
TruthfulQAunassessed51.6
WinoGrandeunassessed74.5

Data

This card as JSON · Edit on GitHub