deepseek llm 7B chat

DeepSeek · deepseek/deepseek-llm-7b-chat

ProviderDeepSeek
Familydeepseek
Typellm-chat
Statusactive
Released2023-11-29

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-Challengeunassessed55.7
BIG-Bench Hardunassessed36.3
GPQA Diamondunassessed26.6
GSM8Kunassessed45.9
HellaSwagunassessed79.4
IFEvalunassessed41.7
MATH-500unassessed2.0
MMLU: Abstract Algebraunassessed25.0
MMLU: Anatomyunassessed45.9
MMLU: Astronomyunassessed52.6
MMLU: Business Ethicsunassessed55.0
MMLU: Clinical Knowledgeunassessed53.2
MMLU: College Biologyunassessed50.0
MMLU: College Chemistryunassessed37.0
MMLU: College Computer Scienceunassessed46.0
MMLU: College Mathematicsunassessed31.0
MMLU: College Medicineunassessed49.1
MMLU: College Physicsunassessed29.4
MMLU: Computer Securityunassessed62.0
MMLU: Conceptual Physicsunassessed43.4
MMLU: Econometricsunassessed27.2
MMLU: Electrical Engineeringunassessed45.5
MMLU: Elementary Mathematicsunassessed31.2
MMLU: Formal Logicunassessed33.3
MMLU: Global Factsunassessed25.0
MMLU: High School Biologyunassessed57.1
MMLU: High School Chemistryunassessed35.0
MMLU: High School Computer Scienceunassessed47.0
MMLU: High School European Historyunassessed67.9
MMLU: High School Geographyunassessed67.2
MMLU: High School Government and Politicsunassessed71.5
MMLU: High School Macroeconomicsunassessed46.7
MMLU: High School Mathematicsunassessed30.0
MMLU: High School Microeconomicsunassessed47.5
MMLU: High School Physicsunassessed29.1
MMLU: High School Psychologyunassessed71.2
MMLU: High School Statisticsunassessed43.5
MMLU: High School US Historyunassessed71.1
MMLU: High School World Historyunassessed72.6
MMLU: Human Agingunassessed57.4
MMLU: Human Sexualityunassessed55.7
MMLU: International Lawunassessed66.1
MMLU: Jurisprudenceunassessed63.0
MMLU: Logical Fallaciesunassessed60.7
MMLU: Machine Learningunassessed41.1
MMLU: Managementunassessed65.0
MMLU: Marketingunassessed82.1
MMLU: Medical Geneticsunassessed60.0
MMLU: Miscellaneousunassessed73.1
MMLU: Moral Disputesunassessed59.0
MMLU: Moral Scenariosunassessed30.6
MMLU: Nutritionunassessed52.3
MMLU: Philosophyunassessed55.6
MMLU: Prehistoryunassessed56.5
MMLU-Prounassessed21.3
MMLU: Professional Accountingunassessed36.5
MMLU: Professional Lawunassessed40.7
MMLU: Professional Medicineunassessed46.7
MMLU: Professional Psychologyunassessed52.0
MMLU: Public Relationsunassessed59.1
MMLU: Security Studiesunassessed62.9
MMLU: Sociologyunassessed70.1
MMLU: US Foreign Policyunassessed82.0
MMLU: Virologyunassessed47.6
MMLU: World Religionsunassessed76.0
MuSRunassessed46.7
TruthfulQAunassessed47.9
WinoGrandeunassessed74.9

Data

This card as JSON · Edit on GitHub