Meta Llama 3 8B

Meta · meta/meta-llama-3-8b

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-Challengeunassessed60.2
BIG-Bench Hardunassessed46.0
GPQA Diamondunassessed30.5
GSM8Kunassessed45.2
HellaSwagunassessed82.2
IFEvalunassessed14.6
MATH-500unassessed4.5
MMLU: Abstract Algebraunassessed35.0
MMLU: Anatomyunassessed69.6
MMLU: Astronomyunassessed67.8
MMLU: Business Ethicsunassessed63.0
MMLU: Clinical Knowledgeunassessed75.5
MMLU: College Biologyunassessed77.1
MMLU: College Chemistryunassessed47.0
MMLU: College Computer Scienceunassessed49.0
MMLU: College Mathematicsunassessed33.0
MMLU: College Medicineunassessed63.6
MMLU: College Physicsunassessed49.0
MMLU: Computer Securityunassessed80.0
MMLU: Conceptual Physicsunassessed59.1
MMLU: Econometricsunassessed49.1
MMLU: Electrical Engineeringunassessed64.8
MMLU: Elementary Mathematicsunassessed43.4
MMLU: Formal Logicunassessed47.6
MMLU: Global Factsunassessed37.0
MMLU: High School Biologyunassessed76.8
MMLU: High School Chemistryunassessed54.7
MMLU: High School Computer Scienceunassessed68.0
MMLU: High School European Historyunassessed77.0
MMLU: High School Geographyunassessed80.3
MMLU: High School Government and Politicsunassessed89.1
MMLU: High School Macroeconomicsunassessed65.1
MMLU: High School Mathematicsunassessed40.0
MMLU: High School Microeconomicsunassessed73.5
MMLU: High School Physicsunassessed44.4
MMLU: High School Psychologyunassessed84.8
MMLU: High School Statisticsunassessed57.9
MMLU: High School US Historyunassessed85.8
MMLU: High School World Historyunassessed82.3
MMLU: Human Agingunassessed71.7
MMLU: Human Sexualityunassessed77.1
MMLU: International Lawunassessed85.1
MMLU: Jurisprudenceunassessed75.0
MMLU: Logical Fallaciesunassessed73.6
MMLU: Machine Learningunassessed53.6
MMLU: Managementunassessed87.4
MMLU: Marketingunassessed89.7
MMLU: Medical Geneticsunassessed79.0
MMLU: Miscellaneousunassessed83.0
MMLU: Moral Disputesunassessed74.0
MMLU: Moral Scenariosunassessed41.3
MMLU: Nutritionunassessed76.5
MMLU: Philosophyunassessed74.3
MMLU: Prehistoryunassessed72.5
MMLU-Prounassessed32.1
MMLU: Professional Accountingunassessed49.3
MMLU: Professional Lawunassessed46.7
MMLU: Professional Medicineunassessed72.1
MMLU: Professional Psychologyunassessed72.4
MMLU: Public Relationsunassessed71.8
MMLU: Security Studiesunassessed75.1
MMLU: Sociologyunassessed85.6
MMLU: US Foreign Policyunassessed86.0
MMLU: Virologyunassessed56.0
MMLU: World Religionsunassessed83.0
MuSRunassessed36.1
TruthfulQAunassessed42.9
WinoGrandeunassessed78.5

Data

This card as JSON · Edit on GitHub