Mixtral 8x7B Instruct v0.1

Mistral AI · mistral/mixtral-8x7b-instruct-v0-1

ProviderMistral AI
Familymistral
Typellm-chat
Statusactive
Released2023-12-10

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-Challengeunassessed70.1
BIG-Bench Hardunassessed36.8
GPQA Diamondunassessed27.2
GSM8Kunassessed61.1
HellaSwagunassessed87.6
IFEvalunassessed69.5
MATH-500unassessed40.1
MMLU: Abstract Algebraunassessed42.0
MMLU: Anatomyunassessed66.7
MMLU: Astronomyunassessed78.9
MMLU: Business Ethicsunassessed73.0
MMLU: Clinical Knowledgeunassessed77.7
MMLU: College Biologyunassessed82.6
MMLU: College Chemistryunassessed50.0
MMLU: College Computer Scienceunassessed66.0
MMLU: College Mathematicsunassessed46.0
MMLU: College Medicineunassessed75.7
MMLU: College Physicsunassessed43.1
MMLU: Computer Securityunassessed81.0
MMLU: Conceptual Physicsunassessed66.8
MMLU: Econometricsunassessed61.4
MMLU: Electrical Engineeringunassessed64.8
MMLU: Elementary Mathematicsunassessed47.9
MMLU: Formal Logicunassessed52.4
MMLU: Global Factsunassessed42.0
MMLU: High School Biologyunassessed85.2
MMLU: High School Chemistryunassessed62.1
MMLU: High School Computer Scienceunassessed78.0
MMLU: High School European Historyunassessed80.0
MMLU: High School Geographyunassessed86.9
MMLU: High School Government and Politicsunassessed95.9
MMLU: High School Macroeconomicsunassessed69.7
MMLU: High School Mathematicsunassessed38.9
MMLU: High School Microeconomicsunassessed80.3
MMLU: High School Physicsunassessed47.0
MMLU: High School Psychologyunassessed88.4
MMLU: High School Statisticsunassessed59.7
MMLU: High School US Historyunassessed85.3
MMLU: High School World Historyunassessed84.8
MMLU: Human Agingunassessed75.8
MMLU: Human Sexualityunassessed80.9
MMLU: International Lawunassessed87.6
MMLU: Jurisprudenceunassessed84.3
MMLU: Logical Fallaciesunassessed81.6
MMLU: Machine Learningunassessed57.1
MMLU: Managementunassessed84.5
MMLU: Marketingunassessed92.3
MMLU: Medical Geneticsunassessed77.0
MMLU: Miscellaneousunassessed88.0
MMLU: Moral Disputesunassessed78.0
MMLU: Moral Scenariosunassessed46.0
MMLU: Nutritionunassessed82.0
MMLU: Philosophyunassessed79.7
MMLU: Prehistoryunassessed83.3
MMLU-Prounassessed40.5
MMLU: Professional Accountingunassessed55.3
MMLU: Professional Lawunassessed54.4
MMLU: Professional Medicineunassessed79.4
MMLU: Professional Psychologyunassessed76.5
MMLU: Public Relationsunassessed70.9
MMLU: Security Studiesunassessed77.1
MMLU: Sociologyunassessed89.1
MMLU: US Foreign Policyunassessed90.0
MMLU: Virologyunassessed50.6
MMLU: World Religionsunassessed87.7
MuSRunassessed11.8
TruthfulQAunassessed65.0
WinoGrandeunassessed81.1

Data

This card as JSON · Edit on GitHub