deepseek coder 6.7B base

DeepSeek · deepseek/deepseek-coder-6-7b-base

ProviderDeepSeek
Familydeepseek
Typellm-code
Statusactive
Released2023-10-23

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-Challengeunassessed37.0
GSM8Kunassessed18.0
HellaSwagunassessed53.5
MMLU: Abstract Algebraunassessed33.0
MMLU: Anatomyunassessed40.0
MMLU: Astronomyunassessed35.5
MMLU: Business Ethicsunassessed40.0
MMLU: Clinical Knowledgeunassessed41.1
MMLU: College Biologyunassessed30.6
MMLU: College Chemistryunassessed39.0
MMLU: College Computer Scienceunassessed43.0
MMLU: College Mathematicsunassessed32.0
MMLU: College Medicineunassessed34.7
MMLU: College Physicsunassessed25.5
MMLU: Computer Securityunassessed62.0
MMLU: Conceptual Physicsunassessed35.3
MMLU: Econometricsunassessed29.8
MMLU: Electrical Engineeringunassessed45.5
MMLU: Elementary Mathematicsunassessed31.2
MMLU: Formal Logicunassessed29.4
MMLU: Global Factsunassessed28.0
MMLU: High School Biologyunassessed36.5
MMLU: High School Chemistryunassessed29.6
MMLU: High School Computer Scienceunassessed52.0
MMLU: High School European Historyunassessed37.0
MMLU: High School Geographyunassessed40.4
MMLU: High School Government and Politicsunassessed42.5
MMLU: High School Macroeconomicsunassessed34.6
MMLU: High School Mathematicsunassessed28.9
MMLU: High School Microeconomicsunassessed36.1
MMLU: High School Physicsunassessed27.8
MMLU: High School Psychologyunassessed38.5
MMLU: High School Statisticsunassessed37.0
MMLU: High School US Historyunassessed34.8
MMLU: High School World Historyunassessed32.1
MMLU: Human Agingunassessed38.1
MMLU: Human Sexualityunassessed46.6
MMLU: International Lawunassessed52.9
MMLU: Jurisprudenceunassessed34.3
MMLU: Logical Fallaciesunassessed42.3
MMLU: Machine Learningunassessed27.7
MMLU: Managementunassessed42.7
MMLU: Marketingunassessed63.7
MMLU: Medical Geneticsunassessed47.0
MMLU: Miscellaneousunassessed40.2
MMLU: Moral Disputesunassessed40.5
MMLU: Moral Scenariosunassessed28.9
MMLU: Nutritionunassessed40.2
MMLU: Philosophyunassessed44.1
MMLU: Prehistoryunassessed28.1
MMLU: Professional Accountingunassessed34.8
MMLU: Professional Lawunassessed28.8
MMLU: Professional Medicineunassessed44.9
MMLU: Professional Psychologyunassessed31.7
MMLU: Public Relationsunassessed50.9
MMLU: Security Studiesunassessed42.9
MMLU: Sociologyunassessed45.3
MMLU: US Foreign Policyunassessed49.0
MMLU: Virologyunassessed41.0
MMLU: World Religionsunassessed38.6
TruthfulQAunassessed40.3
WinoGrandeunassessed58.1

Data

This card as JSON · Edit on GitHub