Meta Llama 3 70B Instruct

Nous Research · nous-research/meta-llama-3-70b-instruct

ProviderNous Research
Familyllama
Typellm-chat
Statusactive
Released2024-04-19

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) 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-Challengeunassessed71.4
BIG-Bench Hardunassessed65.5
GPQA Diamondunassessed28.7
GSM8Kunassessed95.0
HellaSwagunassessed85.7
IFEvalunassessed81.0
MATH-500unassessed24.5
MGSM (Multilingual Grade School Math)unassessed91.1
MMLU: Abstract Algebraunassessed51.0
MMLU: Anatomyunassessed77.0
MMLU: Astronomyunassessed93.4
MMLU: Business Ethicsunassessed86.0
MMLU: Clinical Knowledgeunassessed86.8
MMLU: College Biologyunassessed91.0
MMLU: College Chemistryunassessed56.0
MMLU: College Computer Scienceunassessed69.0
MMLU: College Mathematicsunassessed58.0
MMLU: College Medicineunassessed81.5
MMLU: College Physicsunassessed59.8
MMLU: Computer Securityunassessed82.0
MMLU: Conceptual Physicsunassessed81.7
MMLU: Econometricsunassessed72.8
MMLU: Electrical Engineeringunassessed77.9
MMLU: Elementary Mathematicsunassessed70.9
MMLU: Formal Logicunassessed62.7
MMLU: Global Factsunassessed59.0
MMLU: High School Biologyunassessed89.7
MMLU: High School Chemistryunassessed69.0
MMLU: High School Computer Scienceunassessed92.0
MMLU: High School European Historyunassessed86.7
MMLU: High School Geographyunassessed92.9
MMLU: High School Government and Politicsunassessed98.4
MMLU: High School Macroeconomicsunassessed83.8
MMLU: High School Mathematicsunassessed54.4
MMLU: High School Microeconomicsunassessed88.7
MMLU: High School Physicsunassessed62.3
MMLU: High School Psychologyunassessed94.1
MMLU: High School Statisticsunassessed73.6
MMLU: High School US Historyunassessed92.2
MMLU: High School World Historyunassessed92.8
MMLU: Human Agingunassessed82.1
MMLU: Human Sexualityunassessed87.0
MMLU: International Lawunassessed92.6
MMLU: Jurisprudenceunassessed88.0
MMLU: Logical Fallaciesunassessed85.9
MMLU: Machine Learningunassessed70.5
MMLU: Managementunassessed89.3
MMLU: Marketingunassessed93.6
MMLU: Medical Geneticsunassessed92.0
MMLU: Miscellaneousunassessed91.8
MMLU: Moral Disputesunassessed84.4
MMLU: Moral Scenariosunassessed70.8
MMLU: Nutritionunassessed87.6
MMLU: Philosophyunassessed81.4
MMLU: Prehistoryunassessed90.1
MMLU-Prounassessed52.1
MMLU: Professional Accountingunassessed63.8
MMLU: Professional Lawunassessed64.1
MMLU: Professional Medicineunassessed89.0
MMLU: Professional Psychologyunassessed85.3
MMLU: Public Relationsunassessed74.5
MMLU: Security Studiesunassessed81.6
MMLU: Sociologyunassessed92.0
MMLU: US Foreign Policyunassessed92.0
MMLU: Virologyunassessed56.6
MMLU: World Religionsunassessed90.1
MuSRunassessed41.5
TruthfulQAunassessed61.8
WinoGrandeunassessed82.9

Data

This card as JSON · Edit on GitHub