Mixtral 8x22B Instruct v0.1

Mistral AI · mistral/mixtral-8x22b-instruct-v0-1

ProviderMistral AI
Familymistral
Typellm-chat
Statusactive
Released2024-04-16

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-Challengeunassessed72.7
BIG-Bench Hardunassessed48.5
GPQA Diamondunassessed36.1
GSM8Kunassessed88.0
HellaSwagunassessed89.1
IFEvalunassessed77.8
MATH-500unassessed56.2
MMLU: Abstract Algebraunassessed54.0
MMLU: Anatomyunassessed74.8
MMLU: Astronomyunassessed86.2
MMLU: Business Ethicsunassessed77.0
MMLU: Clinical Knowledgeunassessed82.3
MMLU: College Biologyunassessed89.6
MMLU: College Chemistryunassessed56.0
MMLU: College Computer Scienceunassessed70.0
MMLU: College Mathematicsunassessed49.0
MMLU: College Medicineunassessed76.3
MMLU: College Physicsunassessed57.8
MMLU: Computer Securityunassessed81.0
MMLU: Conceptual Physicsunassessed79.1
MMLU: Econometricsunassessed63.2
MMLU: Electrical Engineeringunassessed75.9
MMLU: Elementary Mathematicsunassessed62.4
MMLU: Formal Logicunassessed59.5
MMLU: Global Factsunassessed54.0
MMLU: High School Biologyunassessed90.0
MMLU: High School Chemistryunassessed69.5
MMLU: High School Computer Scienceunassessed86.0
MMLU: High School European Historyunassessed85.5
MMLU: High School Geographyunassessed89.4
MMLU: High School Government and Politicsunassessed96.9
MMLU: High School Macroeconomicsunassessed81.3
MMLU: High School Mathematicsunassessed50.7
MMLU: High School Microeconomicsunassessed87.8
MMLU: High School Physicsunassessed50.3
MMLU: High School Psychologyunassessed92.7
MMLU: High School Statisticsunassessed69.4
MMLU: High School US Historyunassessed89.7
MMLU: High School World Historyunassessed91.6
MMLU: Human Agingunassessed80.3
MMLU: Human Sexualityunassessed88.5
MMLU: International Lawunassessed90.1
MMLU: Jurisprudenceunassessed86.1
MMLU: Logical Fallaciesunassessed87.1
MMLU: Machine Learningunassessed61.6
MMLU: Managementunassessed87.4
MMLU: Marketingunassessed92.7
MMLU: Medical Geneticsunassessed84.0
MMLU: Miscellaneousunassessed89.9
MMLU: Moral Disputesunassessed84.7
MMLU: Moral Scenariosunassessed66.0
MMLU: Nutritionunassessed87.9
MMLU: Philosophyunassessed82.6
MMLU: Prehistoryunassessed87.0
MMLU-Prounassessed52.3
MMLU: Professional Accountingunassessed66.3
MMLU: Professional Lawunassessed60.3
MMLU: Professional Medicineunassessed88.6
MMLU: Professional Psychologyunassessed84.0
MMLU: Public Relationsunassessed77.3
MMLU: Security Studiesunassessed84.5
MMLU: Sociologyunassessed91.5
MMLU: US Foreign Policyunassessed96.0
MMLU: Virologyunassessed59.0
MMLU: World Religionsunassessed90.6
MuSRunassessed18.5
TruthfulQAunassessed68.1
WinoGrandeunassessed85.2

Data

This card as JSON · Edit on GitHub